Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Abstract

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.

ICML 2017. Code at https://github.com/cbfinn/maml, Videos of RL results at https://sites.google.com/view/maml, Blog post at http://bair.berkeley.edu/blog/2017/07/18/learning-to-learn/

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Prototypical Networks for Few-shot Learning
• Theoretical Models of Learning to Learn
• Gradient-based Hyperparameter Optimization through Reversible Learning
• Learning to Remember Rare Events
• Attentive Recurrent Comparators

Cited by in corpus (1475)

• DeepXDE: A deep learning library for solving differential equations
• On the Opportunities and Risks of Foundation Models
• Shortcut Learning in Deep Neural Networks
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• An Introduction to Deep Reinforcement Learning
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Searching for Activation Functions
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Social physics
• How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
• On First-Order Meta-Learning Algorithms
• Few-Shot Learning with Graph Neural Networks
• Deep Learning for Visual Tracking: A Comprehensive Survey
• Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning
• FedALA: Adaptive Local Aggregation for Personalized Federated Learning
• Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
• An Algorithmic Perspective on Imitation Learning
• Improving Federated Learning Personalization via Model Agnostic Meta Learning
• Personalized Federated Learning: A Meta-Learning Approach
• Fair Resource Allocation in Federated Learning
• Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
• A Survey on Deep Learning Techniques for Stereo-based Depth Estimation
• Advances and Challenges in Conversational Recommender Systems: A Survey
• Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
• Three Approaches for Personalization with Applications to Federated Learning
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Adversarial Attack and Defense on Graph Data: A Survey
• Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds
• LEAF: A Benchmark for Federated Settings
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation
• A Survey of Knowledge-Enhanced Text Generation
• Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Federated Learning of a Mixture of Global and Local Models
• A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments
• Towards Out-Of-Distribution Generalization: A Survey
• Deep Learning for Generic Object Detection: A Survey
• Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control
• Learning to Self-Train for Semi-Supervised Few-Shot Classification
• Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
• Adaptive Aggregation Networks for Class-Incremental Learning
• A survey on Semi-, Self- and Unsupervised Learning for Image Classification
• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
• Personalized Federated Learning with Moreau Envelopes
• A Survey of Machine Learning for Computer Architecture and Systems
• Meta-Learning with Latent Embedding Optimization
• Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
• TADAM: Task dependent adaptive metric for improved few-shot learning
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning
• A Closer Look at Few-shot Classification
• Free Lunch for Few-shot Learning: Distribution Calibration
• A Field Guide to Federated Optimization
• Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
• Unsupervised Learning via Meta-Learning
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• Learning and Evaluating General Linguistic Intelligence
• Bayesian Model-Agnostic Meta-Learning
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• Few-Shot Graph Learning for Molecular Property Prediction
• Transfer Learning in Deep Reinforcement Learning: A Survey
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
• Meta-learning with differentiable closed-form solvers
• Reinforcement Learning for Angle-Only Intercept Guidance of Maneuvering Targets
• Game-Theoretic Multiagent Reinforcement Learning
• Domain Generalization by Marginal Transfer Learning
• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• Evolved Policy Gradients
• Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic Review
• Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
• Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning
• Abstraction and Analogy-Making in Artificial Intelligence
• Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
• The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies
• Biomedical Question Answering: A Survey of Approaches and Challenges
• Adaptive Guidance and Integrated Navigation with Reinforcement Meta-Learning
• Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
• Robust High-dimensional Memory-augmented Neural Networks
• Assessing Generalization in Deep Reinforcement Learning
• MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
• Meta Reinforcement Learning with Latent Variable Gaussian Processes
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Bilevel Programming for Hyperparameter Optimization and Meta-Learning
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
• Incremental Object Detection via Meta-Learning
• MetaSleepLearner: A Pilot Study on Fast Adaptation of Bio-signals-Based Sleep Stage Classifier to New Individual Subject Using Meta-Learning
• Sample Efficient Adaptive Text-to-Speech
• Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloads
• Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
• Deep Meta-Learning: Learning to Learn in the Concept Space
• Few-Shot Segmentation Propagation with Guided Networks
• A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms
• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• MetaPoison: Practical General-purpose Clean-label Data Poisoning
• Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
• Self-Supervised Generalisation with Meta Auxiliary Learning
• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Learning to Walk in the Real World with Minimal Human Effort
• Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
• Seeker based Adaptive Guidance via Reinforcement Meta-Learning Applied to Asteroid Close Proximity Operations
• Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations
• Generalized Inner Loop Meta-Learning
• Towards a universal neural network encoder for time series
• Efficient Exploration via State Marginal Matching
• Coresets via Bilevel Optimization for Continual Learning and Streaming
• SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Functional Regularisation for Continual Learning with Gaussian Processes
• In Search of Lost Domain Generalization
• TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
• Universal Planning Networks
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
• How to train your MAML
• A novel meta-learning initialization method for physics-informed neural networks
• Gotta Learn Fast: A New Benchmark for Generalization in RL
• Stochastic Hyperparameter Optimization through Hypernetworks
• Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation
• Machine learning for industrial sensing and control: A survey and practical perspective
• Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
• Fast Federated Learning by Balancing Communication Trade-Offs
• Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models
• Subgraph Federated Learning with Missing Neighbor Generation
• Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
• Distilled One-Shot Federated Learning
• Unnoticeable Backdoor Attacks on Graph Neural Networks
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
• Meta-Learning without Memorization
• Dynamic Few-Shot Visual Learning without Forgetting
• Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
• Self-supervised Knowledge Distillation for Few-shot Learning
• Few-Shot Learning with Geometric Constraints
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
• How to Retrain Recommender System? A Sequential Meta-Learning Method
• Decoupled Novel Object Captioner
• From Learning to Meta-Learning: Reduced Training Overhead and Complexity for Communication Systems
• Finetuned Language Models Are Zero-Shot Learners
• MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning
• An Overview of Human Activity Recognition Using Wearable Sensors: Healthcare and Artificial Intelligence
• Meta Balanced Network for Fair Face Recognition
• Meta-Learning with Warped Gradient Descent
• Domain Generalization via Optimal Transport with Metric Similarity Learning
• On the Theory of Transfer Learning: The Importance of Task Diversity
• One-Shot Instance Segmentation
• Fast Facial Landmark Detection and Applications: A Survey
• Discriminative Adversarial Domain Generalization with Meta-learning based Cross-domain Validation
• Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting
• VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
• Few-Shot Learning Through an Information Retrieval Lens
• Lower Bounds and Optimal Algorithms for Personalized Federated Learning
• Meta-Learning to Communicate: Fast End-to-End Training for Fading Channels
• Meta-learning for Few-shot Natural Language Processing: A Survey
• Lifelong Incremental Reinforcement Learning with Online Bayesian Inference
• Cycle Self-Training for Domain Adaptation
• Discovering Reinforcement Learning Algorithms
• Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
• BOIL: Towards Representation Change for Few-shot Learning
• Learning Functional Priors and Posteriors from Data and Physics
• Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
• DualNet: Continual Learning, Fast and Slow
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• Improving Generalization in Meta Reinforcement Learning using Learned Objectives
• CrossTransformers: spatially-aware few-shot transfer
• Six Degree-of-Freedom Body-Fixed Hovering over Unmapped Asteroids via LIDAR Altimetry and Reinforcement Meta-Learning
• Meta reinforcement learning as task inference
• Multi-level Second-order Few-shot Learning
• Task Agnostic Continual Learning via Meta Learning
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• Small Sample Learning in Big Data Era
• Neurosymbolic Reinforcement Learning and Planning: A Survey
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling
• A Universal Representation Transformer Layer for Few-Shot Image Classification
• Neuromorphic Hardware learns to learn
• On Warm-Starting Neural Network Training
• Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech
• Few-shot Text Classification with Distributional Signatures
• GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learning
• Alpha MAML: Adaptive Model-Agnostic Meta-Learning
• MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation
• Unsupervised Meta-Learning for Reinforcement Learning
• A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic
• Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
• Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization
• Conditional Neural Processes
• Unsupervised Deep Representation Learning and Few-Shot Classification of PolSAR Images
• Provable Meta-Learning of Linear Representations
• Learning Scheduling Algorithms for Data Processing Clusters
• ES-MAML: Simple Hessian-Free Meta Learning
• End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learning
• One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
• Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating
• Adaptive Siamese Tracking with a Compact Latent Network
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• An empirical investigation of the challenges of real-world reinforcement learning
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Weight Poisoning Attacks on Pre-trained Models
• FedBABU: Towards Enhanced Representation for Federated Image Classification
• Transductive Information Maximization For Few-Shot Learning
• ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learning
• Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images
• Query-efficient Meta Attack to Deep Neural Networks
• Cross-Market Product Recommendation
• Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning
• Deep Learning Theory Review: An Optimal Control and Dynamical Systems Perspective
• Meta-Learning Requires Meta-Augmentation
• Universal Neural Machine Translation for Extremely Low Resource Languages
• An Automated Scanning Transmission Electron Microscope Guided by Sparse Data Analytics
• ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Users
• Meta-Reinforcement Learning for the Tuning of PI Controllers: An Offline Approach
• Rectifying the Shortcut Learning of Background for Few-Shot Learning
• Learning to Make Analogies by Contrasting Abstract Relational Structure
• A Survey of Optimization Methods from a Machine Learning Perspective
• K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
• Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning
• Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Survey
• Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
• Effective Diversity in Population Based Reinforcement Learning
• A critical look at the current train/test split in machine learning
• FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
• Optimizing Millions of Hyperparameters by Implicit Differentiation
• Compositional generalization through meta sequence-to-sequence learning
• Learning Neural Causal Models from Unknown Interventions
• Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering
• Understanding Short-Horizon Bias in Stochastic Meta-Optimization
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
• Subspace Regularizers for Few-Shot Class Incremental Learning
• Recent Advances in Zero-shot Recognition
• Learning the Travelling Salesperson Problem Requires Rethinking Generalization
• Recent Advances of Continual Learning in Computer Vision: An Overview
• Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
• Fast and Scalable Human Pose Estimation using mmWave Point Cloud
• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
• Quantum Architecture Search with Meta-learning
• Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning
• Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
• DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
• Exploring Domain Shift in Extractive Text Summarization
• Knowledge Graph Transfer Network for Few-Shot Recognition
• MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
• learn2learn: A Library for Meta-Learning Research
• A Comprehensive Overview and Survey of Recent Advances in Meta-Learning
• Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation
• Learning from Few Samples: A Survey
• Meta-Gradient Reinforcement Learning with an Objective Discovered Online
• Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
• Grounded Language Learning Fast and Slow
• Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges
• Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning
• Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
• Fairness and Accuracy in Federated Learning
• Learning to Guide: Guidance Law Based on Deep Meta-learning and Model Predictive Path Integral Control
• Unicorn: Continual Learning with a Universal, Off-policy Agent
• Few-Shot Goal Inference for Visuomotor Learning and Planning
• CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
• Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
• GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
• Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning
• La-MAML: Look-ahead Meta Learning for Continual Learning
• TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
• Personalized Federated Learning using Hypernetworks
• MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation
• From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
• Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs
• Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future
• Negative Margin Matters: Understanding Margin in Few-shot Classification
• Learning to Optimize Domain Specific Normalization for Domain Generalization
• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Meta-learning Pseudo-differential Operators with Deep Neural Networks
• Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
• Been There, Done That: Meta-Learning with Episodic Recall
• A Self-Tuning Actor-Critic Algorithm
• Few-Shot Keyword Spotting With Prototypical Networks
• Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learning
• Modular meta-learning
• Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning
• Towards Fast, Accurate and Stable 3D Dense Face Alignment
• Meta-Graph: Few Shot Link Prediction via Meta Learning
• Embedding Model Based Fast Meta Learning for Downlink Beamforming Adaptation
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks
• Reinforcement Meta-Learning for Interception of Maneuvering Exoatmospheric Targets with Parasitic Attitude Loop
• BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation
• Meta Reinforcement Learning for Optimal Design of Legged Robots
• When is invariance useful in an Out-of-Distribution Generalization problem ?
• Revisiting Fine-tuning for Few-shot Learning
• Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
• Incremental Few-Shot Learning with Attention Attractor Networks
• A Tutorial on Ultra-Reliable and Low-Latency Communications in 6G: Integrating Domain Knowledge into Deep Learning
• Efficient Continual Learning with Modular Networks and Task-Driven Priors
• Learning to Defend by Learning to Attack
• Controllable Semantic Parsing via Retrieval Augmentation
• Efficiently Identifying Task Groupings for Multi-Task Learning
• Heterogeneous Multi-task Learning with Expert Diversity
• Prediction Calibration for Generalized Few-shot Semantic Segmentation
• The Variational Homoencoder: Learning to learn high capacity generative models from few examples
• AutoLoss: Learning Discrete Schedules for Alternate Optimization
• Meta-Learned Confidence for Few-shot Learning
• CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process
• Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings
• Meta-Learning for Low-Resource Neural Machine Translation
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Data Efficient Reinforcement Learning for Legged Robots
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning
• Torchmeta: A Meta-Learning library for PyTorch
• Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility
• Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Semi-supervised Cross-domain Neural Networks for Indoor Environment
• Semi-Synchronous Personalized Federated Learning over Mobile Edge Networks
• Accelerating physics-informed neural network based 1D arc simulation by meta learning
• Meta-Consolidation for Continual Learning
• Continual Learning with Adaptive Weights (CLAW)
• GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
• Data Augmentation for Meta-Learning
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
• Adversarial Meta-Learning
• MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
• Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
• Episodic Training for Domain Generalization
• Improved Schemes for Episodic Memory-based Lifelong Learning
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• Design of a Graphical User Interface for Few-Shot Machine Learning Classification of Electron Microscopy Data
• Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning
• Deep Active Learning for Computer Vision: Past and Future
• Prototype Mixture Models for Few-shot Semantic Segmentation
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity
• Part-aware Prototype Network for Few-shot Semantic Segmentation
• Metalearned Neural Memory
• Restoring Negative Information in Few-Shot Object Detection
• Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
• Meta-Learning by the Baldwin Effect
• Meta Continual Learning
• Diverse Few-Shot Text Classification with Multiple Metrics
• DFSeer: A Visual Analytics Approach to Facilitate Model Selection for Demand Forecasting
• A Closer Look at Few-Shot 3D Point Cloud Classification
• Meta-Learning Representations for Continual Learning
• Auto-Meta: Automated Gradient Based Meta Learner Search
• Neural Relational Inference with Fast Modular Meta-learning
• Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
• A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
• Improved Meta Learning for Low Resource Speech Recognition
• Meta Dynamic Pricing: Transfer Learning Across Experiments
• Meta-learning Based Beamforming Design for MISO Downlink
• TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning
• Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• DPGN: Distribution Propagation Graph Network for Few-shot Learning
• RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
• Federated Reconstruction: Partially Local Federated Learning
• Learning to Explore with Meta-Policy Gradient
• Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
• Task-Robust Model-Agnostic Meta-Learning
• Meta-trained agents implement Bayes-optimal agents
• Learning How to Demodulate from Few Pilots via Meta-Learning
• Meta-Learning Symmetries by Reparameterization
• Image Deformation Meta-Networks for One-Shot Learning
• Deep Reinforcement and InfoMax Learning
• Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
• Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
• ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning
• Large Margin Few-Shot Learning
• Recurrent Attentive Neural Process for Sequential Data
• Probabilistic Model-Agnostic Meta-Learning
• A Comprehensive Survey of Multilingual Neural Machine Translation
• Prototype Refinement Network for Few-Shot Segmentation
• Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
• CTU Depth Decision Algorithms for HEVC: A Survey
• MetaPix: Few-Shot Video Retargeting
• DAWSON: A Domain Adaptive Few Shot Generation Framework
• Automated Relational Meta-learning
• Real-World Single Image Super-Resolution: A Brief Review
• Information-Theoretic Generalization Bounds for Meta-Learning and Applications
• Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
• Meta-Learning Deep Energy-Based Memory Models
• Adaptive Gradient-Based Meta-Learning Methods
• Sill-Net: Feature Augmentation with Separated Illumination Representation
• Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data
• Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
• Metalearning with Hebbian Fast Weights
• Penalty Method for Inversion-Free Deep Bilevel Optimization
• Collective optimization for variational quantum eigensolvers
• Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments
• Meta-Learning through Hebbian Plasticity in Random Networks
• A Baseline for Few-Shot Image Classification
• Doing More with Less: Overcoming Data Scarcity for POI Recommendation via Cross-Region Transfer
• Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation
• Automated Self-Supervised Learning for Graphs
• Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments
• Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition
• Single Episode Policy Transfer in Reinforcement Learning
• Fast Parametric Learning with Activation Memorization
• Meta-Learning for Few-Shot Land Cover Classification
• Differentially Private Meta-Learning
• Locality and compositionality in zero-shot learning
• Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
• General Value Function Networks
• MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
• Few-shot Learning with Meta Metric Learners
• Internet Congestion Control via Deep Reinforcement Learning
• On the Outsized Importance of Learning Rates in Local Update Methods
• Meta-Learning Mean Functions for Gaussian Processes
• Domain Adaptive Dialog Generation via Meta Learning
• Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
• Generalization in Transfer Learning
• Learning latent state representation for speeding up exploration
• Accelerating Quadratic Optimization with Reinforcement Learning
• Backdoor Attacks on Federated Meta-Learning
• BERT Learns (and Teaches) Chemistry
• Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
• Feature Learning in Infinite-Width Neural Networks
• A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges
• Deep Learning to Estimate Permeability using Geophysical Data
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
• Explanation-Guided Training for Cross-Domain Few-Shot Classification
• Meta-Adaptive Nonlinear Control: Theory and Algorithms
• Enhancing Few-shot Image Classification with Cosine Transformer
• A Practical Guide to Multi-Objective Reinforcement Learning and Planning
• Online Meta-Critic Learning for Off-Policy Actor-Critic Methods
• Learning Models of Individual Behavior in Chess
• A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning
• MetaLabelNet: Learning to Generate Soft-Labels from Noisy-Labels
• Multitask Learning for Emotion and Personality Detection
• Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching
• One-Shot Object Detection without Fine-Tuning
• Meta-Reinforcement Learning Robust to Distributional Shift via Model Identification and Experience Relabeling
• Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
• Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
• Graph Inference Learning for Semi-supervised Classification
• Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization
• A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
• NLP in FinTech Applications: Past, Present and Future
• On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
• Few-Shot Speaker Identification Using Lightweight Prototypical Network with Feature Grouping and Interaction
• Learning to Learn Variational Semantic Memory
• RelationNet2: Deep Comparison Columns for Few-Shot Learning
• A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems
• Interpretable Deep Learning under Fire
• Flexible Dataset Distillation: Learn Labels Instead of Images
• Wandering Within a World: Online Contextualized Few-Shot Learning
• Self-training for Few-shot Transfer Across Extreme Task Differences
• Regularization Matters in Policy Optimization
• Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation
• Observational Overfitting in Reinforcement Learning
• Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
• Behavior Self-Organization Supports Task Inference for Continual Robot Learning
• RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning
• One-Shot Relational Learning for Knowledge Graphs
• Implicit Model Specialization through DAG-based Decentralized Federated Learning
• Meta-Learning for Stochastic Gradient MCMC
• Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition
• MICK: A Meta-Learning Framework for Few-shot Relation Classification with Small Training Data
• Few-shot Action Recognition with Permutation-invariant Attention
• Adaptive Deep Kernel Learning
• Truncated Back-propagation for Bilevel Optimization
• How to Train Your MAML to Excel in Few-Shot Classification
• Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates
• Relational Generalized Few-Shot Learning
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding
• When MAML Can Adapt Fast and How to Assist When It Cannot
• Recent Advances in Neural Program Synthesis
• Induction Networks for Few-Shot Text Classification
• Low-Resources Project-Specific Code Summarization
• A Broader Study of Cross-Domain Few-Shot Learning
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics
• Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
• RoboNet: Large-Scale Multi-Robot Learning
• Meta-learning curiosity algorithms
• Sampling-based Reachability Analysis: A Random Set Theory Approach with Adversarial Sampling
• Adaptive Masked Proxies for Few-Shot Segmentation
• Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
• Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
• Prototype Rectification for Few-Shot Learning
• When Does Self-supervision Improve Few-shot Learning?
• Specialized federated learning using a mixture of experts
• Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set
• On Learning and Learned Data Representation by Capsule Networks
• Meta-Learning with Sparse Experience Replay for Lifelong Language Learning
• From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)
• KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences
• Lower Bounds and Accelerated Algorithms for Bilevel Optimization
• Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
• Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients
• Transforming task representations to perform novel tasks
• Model-based Adversarial Meta-Reinforcement Learning
• Variational Rectification Inference for Learning with Noisy Labels
• On Episodes, Prototypical Networks, and Few-shot Learning
• Gradient Matching for Domain Generalization
• Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning
• Unsupervised Few-shot Learning via Self-supervised Training
• Experience-Embedded Visual Foresight
• Dynamic Relevance Learning for Few-Shot Object Detection
• Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rules
• AReLU: Attention-based Rectified Linear Unit
• A Comparative Review of Recent Few-Shot Object Detection Algorithms
• A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark
• The effects of negative adaptation in Model-Agnostic Meta-Learning
• Concurrent Meta Reinforcement Learning
• Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis
• Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
• Behavior Priors for Efficient Reinforcement Learning
• Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning
• Deep Learning for Embodied Vision Navigation: A Survey
• Few-shot Classification via Adaptive Attention
• Random Hypervolume Scalarizations for Provable Multi-Objective Black Box Optimization
• Few-Shot Learning for Road Object Detection
• Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
• Higher-Order Function Networks for Learning Composable 3D Object Representations
• Meta-Learning with Graph Neural Networks: Methods and Applications
• A Meta-Learning-based Trajectory Tracking Framework for UAVs under Degraded Conditions
• MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters
• Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
• On Training Implicit Models
• Toward Multimodal Model-Agnostic Meta-Learning
• ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning
• Making Graph Neural Networks Worth It for Low-Data Molecular Machine Learning
• Planar Robot Casting with Real2Sim2Real Self-Supervised Learning
• Few-shot Learning for Time-series Forecasting
• Self-Attentional Credit Assignment for Transfer in Reinforcement Learning
• Reconciling meta-learning and continual learning with online mixtures of tasks
• A Meta-Reinforcement Learning Approach to Process Control
• A Meta-Learning Framework for Generalized Zero-Shot Learning
• Sequential Scenario-Specific Meta Learner for Online Recommendation
• A Theoretical Analysis of the Number of Shots in Few-Shot Learning
• Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
• Learning Fast Adaptation with Meta Strategy Optimization
• Balancing Training for Multilingual Neural Machine Translation
• Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning
• Deep Transfer Learning Based Downlink Channel Prediction for FDD Massive MIMO Systems
• Fixed-MAML for Few Shot Classification in Multilingual Speech Emotion Recognition
• A Closer Look at Prototype Classifier for Few-shot Image Classification
• Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
• Reducing the variance in online optimization by transporting past gradients
• A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
• Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization
• EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking
• Fast Efficient Hyperparameter Tuning for Policy Gradients
• Real-Time Model Calibration with Deep Reinforcement Learning
• ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control
• Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains
• Deep Metric Transfer for Label Propagation with Limited Annotated Data
• A Blockchain-based Reliable Federated Meta-learning for Metaverse: A Dual Game Framework
• Meta-learning autoencoders for few-shot prediction
• p-Meta: Towards On-device Deep Model Adaptation
• How Important is the Train-Validation Split in Meta-Learning?
• Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
• Dynamic Regret of Policy Optimization in Non-stationary Environments
• Offline Meta-Reinforcement Learning with Advantage Weighting
• Meta-Learning with Fewer Tasks through Task Interpolation
• openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer
• Few-shot Quality-Diversity Optimization
• When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification
• Network Architecture Search for Domain Adaptation
• Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition
• Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
• Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?
• Isometric Propagation Network for Generalized Zero-shot Learning
• Scalable Bayesian Meta-Learning through Generalized Implicit Gradients
• Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
• A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning
• Learning to learn via Self-Critique
• Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting
• lamBERT: Language and Action Learning Using Multimodal BERT
• Learning and Planning with a Semantic Model
• Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
• Learning to Learn with Variational Information Bottleneck for Domain Generalization
• Challenges of Applying Deep Reinforcement Learning in Dynamic Dispatching
• M${}^3$RL: Mind-aware Multi-agent Management Reinforcement Learning
• Graph Meta Learning via Local Subgraphs
• Meta-Learning surrogate models for sequential decision making
• Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing
• Multi-task Learning via Adaptation to Similar Tasks for Mortality Prediction of Diverse Rare Diseases
• Similarity R-C3D for Few-shot Temporal Activity Detection
• Learning to Synthesize Programs as Interpretable and Generalizable Policies
• Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
• Region Comparison Network for Interpretable Few-shot Image Classification
• One-Shot Object Localization Using Learnt Visual Cues via Siamese Networks
• Shaping Visual Representations with Attributes for Few-Shot Recognition
• On Tilted Losses in Machine Learning: Theory and Applications
• Imitation Learning: Progress, Taxonomies and Challenges
• Multi-task Batch Reinforcement Learning with Metric Learning
• Stochastic Prototype Embeddings
• SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
• Learning Action-Transferable Policy with Action Embedding
• Improved Bilevel Model: Fast and Optimal Algorithm with Theoretical Guarantee
• Uncertainty in Multitask Transfer Learning
• Improving Generalization via Scalable Neighborhood Component Analysis
• Gradient Agreement as an Optimization Objective for Meta-Learning
• Complementary Meta-Reinforcement Learning for Fault-Adaptive Control
• L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout
• Context Meta-Reinforcement Learning via Neuromodulation
• Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization
• Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
• Cross-domain few-shot learning with unlabelled data
• An Investigation of Few-Shot Learning in Spoken Term Classification
• AOL: Adaptive Online Learning for Human Trajectory Prediction in Dynamic Video Scenes
• Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
• Generalizing from a few environments in safety-critical reinforcement learning
• Modularity in Deep Learning: A Survey
• Continuous Meta-Learning without Tasks
• Weak-shot Fine-grained Classification via Similarity Transfer
• Evolvability ES: Scalable and Direct Optimization of Evolvability
• Cross-domain Few-shot Learning with Task-specific Adapters
• MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering
• Medical Coding with Biomedical Transformer Ensembles and Zero/Few-shot Learning
• Representation based meta-learning for few-shot spoken intent recognition
• MetaCURE: Meta Reinforcement Learning with Empowerment-Driven Exploration
• One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
• Learning Portable Representations for High-Level Planning
• Meta-Amortized Variational Inference and Learning
• Multi-NeuS: 3D Head Portraits from Single Image with Neural Implicit Functions
• Modeling and Optimization Trade-off in Meta-learning
• Weighted Meta-Learning
• Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
• Offline Meta Learning of Exploration
• Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning
• Revisiting Few-shot Activity Detection with Class Similarity Control
• Meta Reinforcement Learning with Task Embedding and Shared Policy
• Supervised Contrastive Learning for Accented Speech Recognition
• Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
• Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
• Meta-hallucinator: Towards Few-Shot Cross-Modality Cardiac Image Segmentation
• Dual-Awareness Attention for Few-Shot Object Detection
• Stateless Neural Meta-Learning using Second-Order Gradients
• Efficient Graph Deep Learning in TensorFlow with tf_geometric
• Magnification Generalization for Histopathology Image Embedding
• Few-Shot Viewpoint Estimation
• Learning to Impute: A General Framework for Semi-supervised Learning
• Meta-MgNet: Meta Multigrid Networks for Solving Parameterized Partial Differential Equations
• Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
• Modular Meta-Learning with Shrinkage
• Meta-learnt priors slow down catastrophic forgetting in neural networks
• MM-FSOD: Meta and metric integrated few-shot object detection
• Editable Neural Networks
• Context-Aware Safe Reinforcement Learning for Non-Stationary Environments
• Meta Reasoning over Knowledge Graphs
• Offline Meta-Reinforcement Learning with Online Self-Supervision
• Probabilistic Active Meta-Learning
• Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes
• Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems
• Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
• ARCADe: A Rapid Continual Anomaly Detector
• Guiding Policies with Language via Meta-Learning
• MARF: The Medial Atom Ray Field Object Representation
• DMRO:A Deep Meta Reinforcement Learning-based Task Offloading Framework for Edge-Cloud Computing
• MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation
• Attribute Propagation Network for Graph Zero-shot Learning
• Personalized Federated Learning with Multi-branch Architecture
• Model-Based Inverse Reinforcement Learning from Visual Demonstrations
• Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study
• Meta-Voice: Fast few-shot style transfer for expressive voice cloning using meta learning
• Breaking the Activation Function Bottleneck through Adaptive Parameterization
• Online Structured Meta-learning
• Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
• Curriculum in Gradient-Based Meta-Reinforcement Learning
• Meta Learning Backpropagation And Improving It
• Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning
• Storchastic: A Framework for General Stochastic Automatic Differentiation
• Transformers for One-Shot Visual Imitation
• CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application
• Exploring Exploration: Comparing Children with RL Agents in Unified Environments
• Meta-learning algorithms for Few-Shot Computer Vision
• Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess
• Meta Inverse Reinforcement Learning via Maximum Reward Sharing for Human Motion Analysis
• Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
• Measuring and Harnessing Transference in Multi-Task Learning
• Learning to Learn with Feedback and Local Plasticity
• Meta Dialogue Policy Learning
• Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
• Meta-Learning Multi-task Communication
• Revisiting Few-Shot Learning for Facial Expression Recognition
• Exploiting All Samples in Low-Resource Sentence Classification: Early Stopping and Initialization Parameters
• Few-Shot Representation Learning for Out-Of-Vocabulary Words
• Empirical Bayes Regret Minimization
• Pre-training Text Representations as Meta Learning
• ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation
• Meta-Learning PAC-Bayes Priors in Model Averaging
• Prototype-based Incremental Few-Shot Semantic Segmentation
• Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning
• TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning
• Task-similarity Aware Meta-learning through Nonparametric Kernel Regression
• Neural Snowball for Few-Shot Relation Learning
• When does MAML Work the Best? An Empirical Study on Model-Agnostic Meta-Learning in NLP Applications
• Data-Efficient Mutual Information Neural Estimator
• The Differentiable Cross-Entropy Method
• POSO: Personalized Cold Start Modules for Large-scale Recommender Systems
• Deep Domain-Adversarial Image Generation for Domain Generalisation
• Learning State-Dependent Losses for Inverse Dynamics Learning
• Distributed Multi-agent Meta Learning for Trajectory Design in Wireless Drone Networks
• Lifelong Robotic Reinforcement Learning by Retaining Experiences
• Semi-Supervised Few-Shot Intent Classification and Slot Filling
• Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources
• Structured Prediction for Conditional Meta-Learning
• Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation
• Comparison-Based Convolutional Neural Networks for Cervical Cell/Clumps Detection in the Limited Data Scenario
• Towards a population-informed approach to the definition of data-driven models for structural dynamics
• Meta Feature Modulator for Long-tailed Recognition
• Heuristic-free Optimization of Force-Controlled Robot Search Strategies in Stochastic Environments
• Heterogeneous Learning from Demonstration
• Reward Optimization for Neural Machine Translation with Learned Metrics
• Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning
• Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
• Generalized Adaptation for Few-Shot Learning
• A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
• INR-Arch: A Dataflow Architecture and Compiler for Arbitrary-Order Gradient Computations in Implicit Neural Representation Processing
• Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
• Few-Shot Electronic Health Record Coding through Graph Contrastive Learning
• Weakly-supervised Object Localization for Few-shot Learning and Fine-grained Few-shot Learning
• Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
• Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets
• Towards Generalized and Incremental Few-Shot Object Detection
• Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification
• Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques
• When Is Generalizable Reinforcement Learning Tractable?
• NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification
• Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
• Distance-Based Regularisation of Deep Networks for Fine-Tuning
• Dynamic Scale Inference by Entropy Minimization
• Few-Shot Bayesian Optimization with Deep Kernel Surrogates
• Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning Problem
• Attentive Graph Neural Networks for Few-Shot Learning
• MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
• Model Generalization on COVID-19 Fake News Detection
• Policy Gradient Optimization of Thompson Sampling Policies
• Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis
• Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
• Model-Based Domain Generalization
• Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
• Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models
• Automatic Learning to Detect Concept Drift
• Robust Meta-learning for Mixed Linear Regression with Small Batches
• Weighted Training for Cross-Task Learning
• Small Towers Make Big Differences
• Actor Critic with Differentially Private Critic
• Texture Bias Of CNNs Limits Few-Shot Classification Performance
• Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
• Noether Networks: Meta-Learning Useful Conserved Quantities
• Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation
• Recursive Inference for Variational Autoencoders
• Learning Meta Face Recognition in Unseen Domains
• On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment
• Domain-Adaptive Few-Shot Learning
• Meta-Learning Initializations for Image Segmentation
• AgileNet: Lightweight Dictionary-based Few-shot Learning
• Generalizing meanings from partners to populations: Hierarchical inference supports convention formation on networks
• Unsupervised Transfer Learning via BERT Neuron Selection
• AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
• Transfer Learning and Meta Learning Based Fast Downlink Beamforming Adaptation
• SIRL: Similarity-based Implicit Representation Learning
• Regularizing Trajectory Optimization with Denoising Autoencoders
• HyperNCA: Growing Developmental Networks with Neural Cellular Automata
• Meta-Learning with Adaptive Hyperparameters
• Dynamic Memory Induction Networks for Few-Shot Text Classification
• Looking back to lower-level information in few-shot learning
• Domain Generalization via Semi-supervised Meta Learning
• Reinforcement Learning by Guided Safe Exploration
• A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning
• Incremental Few-Shot Learning for Pedestrian Attribute Recognition
• Boosting Supervision with Self-Supervision for Few-shot Learning
• MxML: Mixture of Meta-Learners for Few-Shot Classification
• Regularized Fine-grained Meta Face Anti-spoofing
• Learning to Adapt Multi-View Stereo by Self-Supervision
• Learning to Learn in a Semi-Supervised Fashion
• ADAIL: Adaptive Adversarial Imitation Learning
• Adaptive Task Sampling for Meta-Learning
• Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy
• Few-Shot Open-Set Recognition using Meta-Learning
• Differentiable Linear Bandit Algorithm
• A Concise Review of Recent Few-shot Meta-learning Methods
• Self-Supervised Deep Visual Odometry with Online Adaptation
• Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
• Few-Shot Meta-Learning on Point Cloud for Semantic Segmentation
• One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video
• Meta Learning Black-Box Population-Based Optimizers
• MetaDelta: A Meta-Learning System for Few-shot Image Classification
• PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior
• Teaching Robots Novel Objects by Pointing at Them
• Few-shot Sequence Learning with Transformers
• Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
• Video Deblurring by Fitting to Test Data
• Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillance
• ASFGNN: Automated Separated-Federated Graph Neural Network
• Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective
• Non-Gaussian Gaussian Processes for Few-Shot Regression
• A Survey of Exploration Methods in Reinforcement Learning
• $k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
• The Role of Global Labels in Few-Shot Classification and How to Infer Them
• Semi-Supervised Hypothesis Transfer for Source-Free Domain Adaptation
• Multiple Meta-model Quantifying for Medical Visual Question Answering
• MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• Improving Parametric Neural Networks for High-Energy Physics (and Beyond)
• Label-Wise Graph Convolutional Network for Heterophilic Graphs
• Formalizing the Generalization-Forgetting Trade-off in Continual Learning
• How Fine-Tuning Allows for Effective Meta-Learning
• Few-NERD: A Few-Shot Named Entity Recognition Dataset
• Generalization Guarantees for Neural Architecture Search with Train-Validation Split
• Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
• Task-Adaptive Neural Network Search with Meta-Contrastive Learning
• Meta-Learning Dynamics Forecasting Using Task Inference
• Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing
• Meta Learning for Few-Shot One-class Classification
• Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
• Information Theoretic Meta Learning with Gaussian Processes
• Neural Complexity Measures
• Learning Robust State Abstractions for Hidden-Parameter Block MDPs
• UFO-BLO: Unbiased First-Order Bilevel Optimization
• Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
• Learning Task-General Representations with Generative Neuro-Symbolic Modeling
• Meta-Learning Bandit Policies by Gradient Ascent
• Weakly-Supervised Reinforcement Learning for Controllable Behavior
• What Can Learned Intrinsic Rewards Capture?
• Learning Deep Parameterized Skills from Demonstration for Re-targetable Visuomotor Control
• Graph Few-shot Learning via Knowledge Transfer
• Transferable Neural Processes for Hyperparameter Optimization
• Chameleon: Learning Model Initializations Across Tasks With Different Schemas
• Continual Learning via Online Leverage Score Sampling
• Learning to Transfer: Unsupervised Meta Domain Translation
• Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
• Adaptive Cross-Modal Few-Shot Learning
• Efficient transfer learning and online adaptation with latent variable models for continuous control
• Cross-Modulation Networks for Few-Shot Learning
• Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
• An empirical study of pretrained representations for few-shot classification
• Few-Shot Unsupervised Continual Learning through Meta-Examples
• MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization
• Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
• Meta Continual Learning via Dynamic Programming
• Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Estimators for Reinforcement Learning
• Learning to Transfer for Traffic Forecasting via Multi-task Learning
• Human and Scene Motion Deblurring using Pseudo-blur Synthesizer
• Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning
• A Fine-Grained Analysis on Distribution Shift
• Deep Bilevel Learning
• Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction
• Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
• A Channel Coding Benchmark for Meta-Learning
• OnlineAugment: Online Data Augmentation with Less Domain Knowledge
• Video Action Recognition Via Neural Architecture Searching
• Few-shot Scene-adaptive Anomaly Detection
• Self-organization of action hierarchy and compositionality by reinforcement learning with recurrent neural networks
• Multitask Learning with Single Gradient Step Update for Task Balancing
• ST${}^2$: Small-data Text Style Transfer via Multi-task Meta-Learning
• Knowledge Guided Metric Learning for Few-Shot Text Classification
• Meta-Reinforcement Learning in Broad and Non-Parametric Environments
• A Brief Survey of Multilingual Neural Machine Translation
• Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
• Regression Networks for Meta-Learning Few-Shot Classification
• Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches: Extended Version
• Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
• Meta Dropout: Learning to Perturb Features for Generalization
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• Meta-Learned Invariant Risk Minimization
• DOB-Net: Actively Rejecting Unknown Excessive Time-Varying Disturbances
• Revisiting Metric Learning for Few-Shot Image Classification
• Difficulty-aware Meta-learning for Rare Disease Diagnosis
• Meta-Learning with Neural Tangent Kernels
• Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
• Skill Transfer in Deep Reinforcement Learning under Morphological Heterogeneity
• FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
• Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach
• Teaching with Commentaries
• Zero-Shot Audio Classification via Semantic Embeddings
• Optimizing Data Usage via Differentiable Rewards
• Procedural Generalization by Planning with Self-Supervised World Models
• Model Primitive Hierarchical Lifelong Reinforcement Learning
• Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer
• Continual Local Replacement for Few-shot Learning
• Learning Dynamics Models for Model Predictive Agents
• Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks
• AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
• Learning to Recommend via Meta Parameter Partition
• Personalised Federated Learning: A Combinational Approach
• Generating Personalized Dialogue via Multi-Task Meta-Learning
• Orthogonal Over-Parameterized Training
• Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research
• On the Importance of Firth Bias Reduction in Few-Shot Classification
• REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents
• Meta-Learning for Relative Density-Ratio Estimation
• SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
• Graceful Degradation and Related Fields
• Gradient-EM Bayesian Meta-learning
• Continual Learning Using World Models for Pseudo-Rehearsal
• Meta-Learning to Cluster
• MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data
• Meta-Model-Based Meta-Policy Optimization
• Learning Prototype-oriented Set Representations for Meta-Learning
• Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning
• NormGrad: Finding the Pixels that Matter for Training
• Concept Learners for Few-Shot Learning
• Auxiliary Learning by Implicit Differentiation
• Distributed Evolution Strategies Using TPUs for Meta-Learning
• Dynamic population-based meta-learning for multi-agent communication with natural language
• Provable Representation Learning for Imitation Learning via Bi-level Optimization
• Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning
• RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problem
• DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
• Conservative Predictions on Noisy Financial Data
• Multi-Level Correlation Network For Few-Shot Image Classification
• One Shot Learning for Speech Separation
• Adaptive Adversarial Training for Meta Reinforcement Learning
• A contrastive rule for meta-learning
• One-Shot Weakly Supervised Video Object Segmentation
• Program Synthesis Guided Reinforcement Learning for Partially Observed Environments
• Online Hyperparameter Meta-Learning with Hypergradient Distillation
• Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains
• CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning
• Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
• Bi-level Score Matching for Learning Energy-based Latent Variable Models
• Learning to Evolve on Dynamic Graphs
• How Does the Task Landscape Affect MAML Performance?
• Reviewing continual learning from the perspective of human-level intelligence
• MAMRL: Exploiting Multi-agent Meta Reinforcement Learning in WAN Traffic Engineering
• Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
• Meta-Learning for Domain Generalization in Semantic Parsing
• Faster Optimization-Based Meta-Learning Adaptation Phase
• MELD: Meta-Reinforcement Learning from Images via Latent State Models
• Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes
• Domain Adaptation of Reinforcement Learning Agents based on Network Service Proximity
• CNN Feature Map Augmentation for Single-Source Domain Generalization
• Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?
• Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data
• Meta Learning to Rank for Sparsely Supervised Queries
• Meta Learning MPC using Finite-Dimensional Gaussian Process Approximations
• Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition
• Learning to See Through Obstructions with Layered Decomposition
• Data-Model-Circuit Tri-Design for Ultra-Light Video Intelligence on Edge Devices
• State-of-the-art Techniques in Deep Edge Intelligence
• Meta Adversarial Perturbations
• Compositional Fine-Grained Low-Shot Learning
• Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning
• NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Control
• What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
• Zero-Shot Compositional Policy Learning via Language Grounding
• Bilevel Optimization for Machine Learning: Algorithm Design and Convergence Analysis
• Disturbance-immune Weight Sharing for Neural Architecture Search
• Self-balanced Learning For Domain Generalization
• CAFENet: Class-Agnostic Few-Shot Edge Detection Network
• Visual Sensation and Perception Computational Models for Deep Learning: State of the art, Challenges and Prospects
• Advancing Renewable Electricity Consumption With Reinforcement Learning
• Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization
• Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification
• Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining
• Click-through Rate Prediction with Auto-Quantized Contrastive Learning
• Block Contextual MDPs for Continual Learning
• Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
• Parameter Prediction for Unseen Deep Architectures
• Gradient Inversion with Generative Image Prior
• Variational Metric Scaling for Metric-Based Meta-Learning
• Hierarchical Expert Networks for Meta-Learning
• Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning
• Blind interactive learning of modulation schemes: Multi-agent cooperation without co-design
• Neuro-Optimization: Learning Objective Functions Using Neural Networks
• Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
• Decoder Choice Network for Meta-Learning
• Reinforcement Learning for Flexibility Design Problems
• Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks
• Similarity of Classification Tasks
• Reducing the Amortization Gap in Variational Autoencoders: A Bayesian Random Function Approach
• Learning Compositional Representation for Few-shot Visual Question Answering
• Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation
• ROAM: Recurrently Optimizing Tracking Model
• Mutual Information State Intrinsic Control
• Conditional Meta-Learning of Linear Representations
• SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
• Inferential Text Generation with Multiple Knowledge Sources and Meta-Learning
• Improved Adversarial Training via Learned Optimizer
• Gradual Relation Network: Decoding Intuitive Upper Extremity Movement Imaginations Based on Few-Shot EEG Learning
• Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning
• High Dimensional Restrictive Federated Model Selection with multi-objective Bayesian Optimization over shifted distributions
• Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
• MPLP: Learning a Message Passing Learning Protocol
• Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification
• Contextualizing Enhances Gradient Based Meta Learning
• Diversity-Driven Extensible Hierarchical Reinforcement Learning
• SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data
• A Foliated View of Transfer Learning
• Improving End-to-End Speech-to-Intent Classification with Reptile
• Few-Shot Learning with Intra-Class Knowledge Transfer
• The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuning
• DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the Loop
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
• Augmented Natural Language for Generative Sequence Labeling
• Learning Invariances for Policy Generalization
• Learning Image Labels On-the-fly for Training Robust Classification Models
• Wider Networks Learn Better Features
• Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation
• Bottom-Up Meta-Policy Search
• MANGA: Method Agnostic Neural-policy Generalization and Adaptation
• Modeling Conceptual Understanding in Image Reference Games
• Multi-Agent Deep Reinforcement Learning with Adaptive Policies
• Optimizing Reusable Knowledge for Continual Learning via Metalearning
• Subspace Representation Learning for Few-shot Image Classification
• Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture
• The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings
• Meta-ViterbiNet: Online Meta-Learned Viterbi Equalization for Non-Stationary Channels
• Model Aggregation via Good-Enough Model Spaces
• Constructing unbiased gradient estimators with finite variance for conditional stochastic optimization
• Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing
• MetaView: Few-shot Active Object Recognition
• ST-MAML: A Stochastic-Task based Method for Task-Heterogeneous Meta-Learning
• Group Equivariant Conditional Neural Processes
• Meta Back-translation
• Model-Agnostic Graph Regularization for Few-Shot Learning
• Gradient Origin Networks
• Auditory Separation of a Conversation from Background via Attentional Gating
• Meta-Learning with Hessian-Free Approach in Deep Neural Nets Training
• An Induced Multi-Relational Framework for Answer Selection in Community Question Answer Platforms
• On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning
• Cross-subject Action Unit Detection with Meta Learning and Transformer-based Relation Modeling
• Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction
• An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset
• Linguistically-Enriched and Context-Aware Zero-shot Slot Filling
• Out-of-Domain Detection for Low-Resource Text Classification Tasks
• The Information Geometry of Unsupervised Reinforcement Learning
• Adversarial Monte Carlo Meta-Learning of Optimal Prediction Procedures
• Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification
• Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces
• Invariant Feature Learning for Sensor-based Human Activity Recognition
• Learning Continually from Low-shot Data Stream
• Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
• Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximation
• Short-Term Stock Price-Trend Prediction Using Meta-Learning
• Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization
• Unsupervised Star Galaxy Classification with Cascade Variational Auto-Encoder
• Bidirectional RNN-based Few Shot Learning for 3D Medical Image Segmentation
• Mutual Information-based State-Control for Intrinsically Motivated Reinforcement Learning
• Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
• Lightweight Relational Embedding in Task-Interpolated Few-Shot Networks for Enhanced Gastrointestinal Disease Classification
• Hierarchical Meta Learning
• Semi-supervised Relation Extraction via Incremental Meta Self-Training
• Semi-Supervised Few-Shot Atomic Action Recognition
• PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators
• Avoiding Tampering Incentives in Deep RL via Decoupled Approval
• PAC Reinforcement Learning without Real-World Feedback
• Multi-Label Few-Shot Learning for Aspect Category Detection
• Bayesian Meta-reinforcement Learning for Traffic Signal Control
• MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
• Hindsight Foresight Relabeling for Meta-Reinforcement Learning
• Transductive Few-Shot Learning: Clustering is All You Need?
• Learning Associative Inference Using Fast Weight Memory
• Zero-Shot Audio Classification with Factored Linear and Nonlinear Acoustic-Semantic Projections
• Model-Agnostic Meta-Learning using Runge-Kutta Methods
• Few-Shot Abstract Visual Reasoning With Spectral Features
• Theoretical bounds on estimation error for meta-learning
• Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images
• Exploration by Maximizing Rényi Entropy for Reward-Free RL Framework
• Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks
• Multi-task Reinforcement Learning in Reproducing Kernel Hilbert Spaces via Cross-learning
• Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
• Few-shot Learning for Spatial Regression
• Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization
• Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF
• Understanding Deep Architectures with Reasoning Layer
• Machine Learning Applications for Therapeutic Tasks with Genomics Data
• Meta-Learning with Network Pruning
• Deep Learning for HDR Imaging: State-of-the-Art and Future Trends
• Learn Faster and Forget Slower via Fast and Stable Task Adaptation
• Uniform Priors for Data-Efficient Transfer
• PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
• Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
• Safe Exploration by Solving Early Terminated MDP
• A Primal-Dual Subgradient Approachfor Fair Meta Learning
• OmniPrint: A Configurable Printed Character Synthesizer
• Few-Shot Learning for Image Classification of Common Flora
• Temporal Alignment Prediction for Few-Shot Video Classification
• Meta-learning for mixed linear regression
• Collision Avoidance Robotics Via Meta-Learning (CARML)
• Predicting the Accuracy of a Few-Shot Classifier
• Stress Testing of Meta-learning Approaches for Few-shot Learning
• Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning
• Interpretable Time-series Classification on Few-shot Samples
• Ubiquitous Acoustic Sensing on Commodity IoT Devices: A Survey
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective
• TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
• How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning
• Multi-step Estimation for Gradient-based Meta-learning
• MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction
• High-order structure preserving graph neural network for few-shot learning
• Automating Predictive Modeling Process using Reinforcement Learning
• MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks
• A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning
• Learning to generate classifiers
• Flying Through a Narrow Gap Using End-to-end Deep Reinforcement Learning Augmented with Curriculum Learning and Sim2Real
• Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification
• CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP
• Knowledge-graph based Proactive Dialogue Generation with Improved Meta-Learning
• Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning
• Meta-Learning for Few-Shot NMT Adaptation
• Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning
• Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations
• MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
• Sequential Learning for Domain Generalization
• Pareto Self-Supervised Training for Few-Shot Learning
• Bayesian Optimization with Approximate Set Kernels
• Meta-CoTGAN: A Meta Cooperative Training Paradigm for Improving Adversarial Text Generation
• PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
• Prototypical quadruplet for few-shot class incremental learning
• Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning
• MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
• Optimization Induced Equilibrium Networks
• Few-shot Intent Classification and Slot Filling with Retrieved Examples
• Model-Agnostic Learning to Meta-Learn
• Contextual HyperNetworks for Novel Feature Adaptation
• Learning to Compare Relation: Semantic Alignment for Few-Shot Learning
• AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
• Single-View 3D Object Reconstruction from Shape Priors in Memory
• VIABLE: Fast Adaptation via Backpropagating Learned Loss
• Amanuensis: The Programmer's Apprentice
• Meta-Learning for One-Class Classification with Few Examples using Order-Equivariant Network
• Learning Generative Prior with Latent Space Sparsity Constraints
• MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning
• Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
• Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection
• X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering
• A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
• Resilient UAV Swarm Communications with Graph Convolutional Neural Network
• Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation
• Personalizing Pre-trained Models
• One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
• Iterative Teaching by Label Synthesis
• Modular meta-learning in abstract graph networks for combinatorial generalization
• Few-shot 3D Point Cloud Semantic Segmentation
• A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View
• Evaluating Meta-Feature Selection for the Algorithm Recommendation Problem
• Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
• Robustness of Meta Matrix Factorization Against Strict Privacy Constraints
• Trainable Class Prototypes for Few-Shot Learning
• Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
• Few-shot Learning for Unsupervised Feature Selection
• Fast Model Editing at Scale
• Meta-Reinforcement Learning for Heuristic Planning
• For high-dimensional hierarchical models, consider exchangeability of effects across covariates instead of across datasets
• Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer
• Neural Fixed-Point Acceleration for Convex Optimization
• Few-Sample Named Entity Recognition for Security Vulnerability Reports by Fine-Tuning Pre-Trained Language Models
• Learning-to-learn non-convex piecewise-Lipschitz functions
• Learning Class-level Prototypes for Few-shot Learning
• Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation
• Infusing Future Information into Monotonic Attention Through Language Models
• CIM: Class-Irrelevant Mapping for Few-Shot Classification
• Task-Adaptive Clustering for Semi-Supervised Few-Shot Classification
• On Hyper-parameter Tuning for Stochastic Optimization Algorithms
• MetaXT: Meta Cross-Task Transfer between Disparate Label Spaces
• Rapid Model Architecture Adaption for Meta-Learning
• Neural Embedding Propagation on Heterogeneous Networks
• Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning
• Data Summarization via Bilevel Optimization
• Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
• Conditional Deep Gaussian Processes: multi-fidelity kernel learning
• Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning
• Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness
• Few Shot Learning with Simplex
• Categorizing Items with Short and Noisy Descriptions using Ensembled Transferred Embeddings
• GCCN: Global Context Convolutional Network
• Fine-grained Image-to-Image Transformation towards Visual Recognition
• Attribute-Modulated Generative Meta Learning for Zero-Shot Classification
• Towards Understanding Residual and Dilated Dense Neural Networks via Convolutional Sparse Coding
• Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution
• NOTMAD: Estimating Bayesian Networks with Sample-Specific Structures and Parameters
• End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization
• WAFFLE: Weighted Averaging for Personalized Federated Learning
• Meta Label Correction for Noisy Label Learning
• Meta Cross-Modal Hashing on Long-Tailed Data
• A Relational Model for One-Shot Classification
• Learning to Rectify for Robust Learning with Noisy Labels
• Free-Form Image Inpainting via Contrastive Attention Network
• Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification
• Large-Scale Meta-Learning with Continual Trajectory Shifting
• Meta-learning Transferable Representations with a Single Target Domain
• Confusable Learning for Large-class Few-Shot Classification
• Graph convolutional networks for learning with few clean and many noisy labels
• On the Expressivity of Neural Networks for Deep Reinforcement Learning
• Debiasing Convolutional Neural Networks via Meta Orthogonalization
• Meta Variational Monte Carlo
• Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis
• System Identification via Meta-Learning in Linear Time-Varying Environments
• Learning a metacognition for object perception
• MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning
• Meta-Learner with Linear Nulling
• BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
• Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators
• Multi-level Similarity Learning for Low-Shot Recognition
• Towards Recognizing New Semantic Concepts in New Visual Domains
• MetaAugment: Sample-Aware Data Augmentation Policy Learning
• Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
• Fair Meta-Learning: Learning How to Learn Fairly
• Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments
• MAME : Model-Agnostic Meta-Exploration
• Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
• Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning
• Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning
• Meta ordinal weighting net for improving lung nodule classification
• Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation
• Identifying Physical Law of Hamiltonian Systems via Meta-Learning
• Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
• Updatable Siamese Tracker with Two-stage One-shot Learning
• Learning Meta Representations for Agents in Multi-Agent Reinforcement Learning
• Fixes That Fail: Self-Defeating Improvements in Machine-Learning Systems
• Deep learning scheme for recovery of broadband microwave photonic receiving systems in transceivers without expert knowledge and system priors
• Out-of-Vocabulary Embedding Imputation with Grounded Language Information by Graph Convolutional Networks
• Meta-Adversarial Inverse Reinforcement Learning for Decision-making Tasks
• Explainability-aided Domain Generalization for Image Classification
• Improved Robustness and Safety for Pre-Adaptation of Meta Reinforcement Learning with Prior Regularization
• Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
• Continual Backprop: Stochastic Gradient Descent with Persistent Randomness
• Few-shot learning via tensor hallucination
• Learning to Learn to be Right for the Right Reasons
• Zero-shot task adaptation by homoiconic meta-mapping
• Knowledge Transferring via Model Aggregation for Online Social Care
• Technical Report: Adaptive Control for Linearizable Systems Using On-Policy Reinforcement Learning
• Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset
• Sufficiently Accurate Model Learning
• Learning to Model Opponent Learning
• Learning Implicit Temporal Alignment for Few-shot Video Classification
• Rapid Structural Pruning of Neural Networks with Set-based Task-Adaptive Meta-Pruning
• Memory Efficient Meta-Learning with Large Images
• Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
• Discrete Few-Shot Learning for Pan Privacy
• Inductive Unsupervised Domain Adaptation for Few-Shot Classification via Clustering
• Context-Based Soft Actor Critic for Environments with Non-stationary Dynamics
• Few-shot Learning with Global Relatedness Decoupled-Distillation
• MetaStyle: Three-Way Trade-Off Among Speed, Flexibility, and Quality in Neural Style Transfer
• Representation based and Attention augmented Meta learning
• What is Going on Inside Recurrent Meta Reinforcement Learning Agents?
• Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data
• Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
• Privacy-Preserving Constrained Domain Generalization via Gradient Alignment
• Click-Based Student Performance Prediction: A Clustering Guided Meta-Learning Approach
• End-to-end One-shot Human Parsing
• Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark
• Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training
• No Regrets for Learning the Prior in Bandits
• Few-Shot Object Detection via Knowledge Transfer
• AdaVocoder: Adaptive Vocoder for Custom Voice
• Uncertainty-Aware Few-Shot Image Classification
• Pre-training with Meta Learning for Chinese Word Segmentation
• TAMPC: A Controller for Escaping Traps in Novel Environments
• Sparse Meta Networks for Sequential Adaptation and its Application to Adaptive Language Modelling
• On the Energy and Communication Efficiency Tradeoffs in Federated and Multi-Task Learning
• A Markov Decision Process Approach to Active Meta Learning
• Interactive Agent Modeling by Learning to Probe
• A Meta-learning based Distribution System Load Forecasting Model Selection Framework
• Meta-Learning Strategies through Value Maximization in Neural Networks
• Extended Radial Basis Function Controller for Reinforcement Learning
• MLANE: Meta-Learning Based Adaptive Network Embedding
• AlphaNet: Improving Long-Tail Classification By Combining Classifiers
• Teaching to Learn: Sequential Teaching of Agents with Inner States
• A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning
• One-step differentiation of iterative algorithms
• Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
• FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
• Learning to Profile: User Meta-Profile Network for Few-Shot Learning
• Self-attention Multi-view Representation Learning with Diversity-promoting Complementarity
• Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
• CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise
• Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?
• Learnable Parameter Similarity
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
• Meta-learning on Spectral Images of Electroencephalogram of Schizophenics
• Meta Reinforcement Learning Based Sensor Scanning in 3D Uncertain Environments for Heterogeneous Multi-Robot Systems
• Compositional federated learning: Applications in distributionally robust averaging and meta learning
• Unfairness Discovery and Prevention For Few-Shot Regression
• Few-shot Object Detection with Feature Attention Highlight Module in Remote Sensing Images
• STDI-Net: Spatial-Temporal Network with Dynamic Interval Mapping for Bike Sharing Demand Prediction
• Context-aware Active Multi-Step Reinforcement Learning
• Learning to Continually Learn Rapidly from Few and Noisy Data
• Continual learning under domain transfer with sparse synaptic bursting
• CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context
• Agent Probing Interaction Policies
• Is Fast Adaptation All You Need?
• Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error
• Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
• Learning Policies for Multilingual Training of Neural Machine Translation Systems
• Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
• AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee
• Connecting Images through Time and Sources: Introducing Low-data, Heterogeneous Instance Retrieval
• Meta-learning of Pooling Layers for Character Recognition
• Learning by Examples Based on Multi-level Optimization
• Task Attended Meta-Learning for Few-Shot Learning
• Meta-Learning with Variational Bayes
• TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
• Automatically Exposing Problems with Neural Dialog Models
• Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation
• Beyond Categorical Label Representations for Image Classification
• Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach
• Prototypical Region Proposal Networks for Few-Shot Localization and Classification
• One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification
• MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction
• Dataset Bias in Few-shot Image Recognition
• An Empirical Framework for Domain Generalization in Clinical Settings
• Robustifying Reinforcement Learning Policies with ${\mathcal{L}}_1$ Adaptive Control
• Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy
• A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters
• Complex Knowledge Base Question Answering: A Survey
• Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability
• Meta Reinforcement Learning with Distribution of Exploration Parameters Learned by Evolution Strategies
• Few-shot Learning for Topic Modeling
• Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis
• TAG: Task-based Accumulated Gradients for Lifelong learning
• Learning with Hyperspherical Uniformity
• Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
• Class Interference Regularization
• Proxy Network for Few Shot Learning
• Neuron Coverage-Guided Domain Generalization
• Learning Reusable Options for Multi-Task Reinforcement Learning
• Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention
• ML-misfit: Learning a robust misfit function for full-waveform inversion using machine learning
• Meta-Forecasting by combining Global Deep Representations with Local Adaptation
• Uniform Sampling over Episode Difficulty
• Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• Meta Auxiliary Learning for Facial Action Unit Detection
• Lifetime policy reuse and the importance of task capacity
• One-shot domain adaptation for semantic face editing of real world images using StyleALAE
• Finding Significant Features for Few-Shot Learning using Dimensionality Reduction
• Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL
• Challenge Closed-book Science Exam: A Meta-learning Based Question Answering System
• Adaptation-Agnostic Meta-Training
• Learning to Learn Morphological Inflection for Resource-Poor Languages
• Graph-LDA: Graph Structure Priors to Improve the Accuracy in Few-Shot Classification
• Probabilistic task modelling for meta-learning
• Ensemble Making Few-Shot Learning Stronger
• Unifying Few- and Zero-Shot Egocentric Action Recognition
• Transfer Bayesian Meta-learning via Weighted Free Energy Minimization
• Transfer Reinforcement Learning across Homotopy Classes
• Training an Interactive Helper
• Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization
• Evolving parametrized Loss for Image Classification Learning on Small Datasets
• Neural Auto-Curricula
• A good body is all you need: avoiding catastrophic interference via agent architecture search
• Channel Relationship Prediction with Forget-Update Module for Few-shot Classification
• GO Hessian for Expectation-Based Objectives
• BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing
• Knowledge accumulating: The general pattern of learning
• Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records
• PICO: Primitive Imitation for COntrol
• Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection
• Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning
• Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
• Gradient-based Hyperparameter Optimization Over Long Horizons
• Few-shot Learning by Exploiting Visual Concepts within CNNs
• Learning Mixtures of Low-Rank Models
• Compressed Sensing via Measurement-Conditional Generative Models
• Provable Lifelong Learning of Representations
• A Meta Reinforcement Learning-based Approach for Self-Adaptive System
• A Few-Shot Sequential Approach for Object Counting
• Meta Learning in the Continuous Time Limit
• UAV-assisted Online Machine Learning over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approach
• Training Efficiency and Robustness in Deep Learning
• Multi-accent Speech Separation with One Shot Learning
• Boosting Few-Shot Classification with View-Learnable Contrastive Learning
• MDFM: Multi-Decision Fusing Model for Few-Shot Learning
• Learning to Transfer: A Foliated Theory
• BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning
• External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery
• MTL2L: A Context Aware Neural Optimiser
• Multimedia Edge Computing
• Learning Shared Dynamics with Meta-World Models
• One-Shot Learning for Language Modelling
• Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty
• MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning
• A Transductive Maximum Margin Classifier for Few-Shot Learning
• GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL
• Domain Agnostic Few-Shot Learning For Document Intelligence
• Using Neural Networks for Programming by Demonstration
• One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learning
• Universality of Gradient Descent Neural Network Training
• Augmented Bi-path Network for Few-shot Learning
• Meta-Learning to Improve Pre-Training
• Meta Adaptation using Importance Weighted Demonstrations
• Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!
• Designing Neural Speaker Embeddings with Meta Learning
• Learning to Generalize to Unseen Tasks with Bilevel Optimization
• [Re] Learning to Learn By Self-Critique
• Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP
• Meta Guided Metric Learner for Overcoming Class Confusion in Few-Shot Road Object Detection
• A Meta-Learned Neuron model for Continual Learning
• Exploiting a Zoo of Checkpoints for Unseen Tasks
• Deep Episodic Value Iteration for Model-based Meta-Reinforcement Learning
• Crowdsourcing with Meta-Workers: A New Way to Save the Budget
• Submodular Meta-Learning
• Cooperative Bi-path Metric for Few-shot Learning
• Meta-learning for Matrix Factorization without Shared Rows or Columns
• Towards Enabling Meta-Learning from Target Models
• State Representation Learning from Demonstration
• Few-shot Learning with LSSVM Base Learner and Transductive Modules
• On sensitivity of meta-learning to support data
• Learning to Learn to Compress
• Corpora Generation for Grammatical Error Correction
• Meta-learning for RIS-assisted NOMA Networks
• An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling
• Far-HO: A Bilevel Programming Package for Hyperparameter Optimization and Meta-Learning
• Meta-Learning for Natural Language Understanding under Continual Learning Framework
• Online Continual Learning in Image Classification: An Empirical Survey
• Multitask Adaptation by Retrospective Exploration with Learned World Models
• Meta-Active Learning for Node Response Prediction in Graphs
• MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization
• Characterizing Policy Divergence for Personalized Meta-Reinforcement Learning
• Towards Data-Free Domain Generalization
• Exploring Task Difficulty for Few-Shot Relation Extraction
• Iterative Semi-parametric Dynamics Model Learning For Autonomous Racing
• Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
• Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data
• Bayesian Meta-Learning Through Variational Gaussian Processes
• Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning
• MetalGAN: a Cluster-based Adaptive Training for Few-Shot Adversarial Colorization
• HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression
• Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models
• Convergence Analysis of Homotopy-SGD for non-convex optimization
• Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework
• Learning Synthetic to Real Transfer for Localization and Navigational Tasks
• Balancing Average and Worst-case Accuracy in Multitask Learning
• Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
• Efficient Automatic Meta Optimization Search for Few-Shot Learning
• Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks
• Diversity Transfer Network for Few-Shot Learning
• Visual Goal-Directed Meta-Learning with Contextual Planning Networks
• Generating meta-learning tasks to evolve parametric loss for classification learning
• Multi-Pair Text Style Transfer on Unbalanced Data
• Adaptive Submodular Meta-Learning
• Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters
• A${}^2$M${}^2$-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognition
• Meta-Learning with Adjoint Methods
• Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding
• One-shot Learning with Absolute Generalization
• Performance-Weighed Policy Sampling for Meta-Reinforcement Learning
• Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition
• Coarse-To-Fine Incremental Few-Shot Learning
• Personalizing Dialogue Agents via Meta-Learning
• Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning
• Learning to Initialize Gradient Descent Using Gradient Descent
• Boosting Black-Box Adversarial Attacks with Meta Learning
• Novelty-Prepared Few-Shot Classification
• Widen The Backdoor To Let More Attackers In
• Realizing Continual Learning through Modeling a Learning System as a Fiber Bundle
• Joint User Activity and Data Detection in Grant-Free NOMA using Generative Neural Networks
• Fast and Effective Adaptation of Facial Action Unit Detection Deep Model
• Meta Internal Learning
• The Sample Complexity of Meta Sparse Regression
• Revisiting Self-Training for Few-Shot Learning of Language Model
• Table-to-Text Natural Language Generation with Unseen Schemas
• On the Practical Consistency of Meta-Reinforcement Learning Algorithms
• Bootstrapped Meta-Learning
• Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
• LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training
• Semi-Supervised Learning with Meta-Gradient
• HMRL: Hyper-Meta Learning for Sparse Reward Reinforcement Learning Problem
• Few-Shot Semantic Parsing for New Predicates
• Edge-Labeling based Directed Gated Graph Network for Few-shot Learning
• Active Refinement for Multi-Label Learning: A Pseudo-Label Approach
• Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
• Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models
• On Data Efficiency of Meta-learning
• Continual Learning of Multi-modal Dynamics with External Memory
• MetaHistoSeg: A Python Framework for Meta Learning in Histopathology Image Segmentation
• Meta-Learning for Koopman Spectral Analysis with Short Time-series
• Few-Shot Meta-Denoising
• A method of supervised learning from conflicting data with hidden contexts
• Dynamic Regret Analysis for Online Meta-Learning