An Overview of Multi-Task Learning in Deep Neural Networks

Abstract

Multi-task learning (MTL) has led to successes in many applications of machine learning, from natural language processing and speech recognition to computer vision and drug discovery. This article aims to give a general overview of MTL, particularly in deep neural networks. It introduces the two most common methods for MTL in Deep Learning, gives an overview of the literature, and discusses recent advances. In particular, it seeks to help ML practitioners apply MTL by shedding light on how MTL works and providing guidelines for choosing appropriate auxiliary tasks.

arXiv comment14 pages, 8 figures

References in corpus (7)

• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Massively Multitask Networks for Drug Discovery
• Deep Voice: Real-time Neural Text-to-Speech
• Deep Multi-task Representation Learning: A Tensor Factorisation Approach
• Bayesian Multitask Learning with Latent Hierarchies
• A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
• Distributed Multi-Task Relationship Learning

Cited by in corpus (445)

• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Deep Learning-based Vehicle Behaviour Prediction For Autonomous Driving Applications: A Review
• Multi-Task Learning with Deep Neural Networks: A Survey
• A Survey of Sound Source Localization with Deep Learning Methods
• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions
• Regularization for Deep Learning: A Taxonomy
• Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images
• Auxiliary Tasks in Multi-task Learning
• Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
• Meta-learning with differentiable closed-form solvers
• AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
• Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network
• Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation
• Variational Federated Multi-Task Learning
• Graph Attention Multi-Layer Perceptron
• Assessing Generalization in Deep Reinforcement Learning
• Blind Backdoors in Deep Learning Models
• A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects
• Review: Deep Learning in Electron Microscopy
• Gradient Surgery for Multi-Task Learning
• WT5?! Training Text-to-Text Models to Explain their Predictions
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• Fast Online Object Tracking and Segmentation: A Unifying Approach
• Deep Adaptive Learning for Writer Identification based on Single Handwritten Word Images
• Applying Deep Learning To Airbnb Search
• Self-Supervised Generalisation with Meta Auxiliary Learning
• A review on vision-based analysis for automatic dietary assessment
• MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification
• A unified framework for machine learning collective variables for enhanced sampling simulations: $\text{mlcolvar}$
• Deep Learning for Genomics: A Concise Overview
• Deep Learning-Based Human Pose Estimation: A Survey
• Faster Training of Mask R-CNN by Focusing on Instance Boundaries
• CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences
• Multi-task learning for natural language processing in the 2020s: where are we going?
• Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-based Convolutional Neural Networks
• Annotating Columns with Pre-trained Language Models
• Gradient Vaccine: Investigating and Improving Multi-task Optimization in Massively Multilingual Models
• Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation
• ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
• Finetuned Language Models Are Zero-Shot Learners
• Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark
• Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
• Multi-Task Learning for Sequence Tagging: An Empirical Study
• Automatic Detection of Malware-Generated Domains with Recurrent Neural Models
• Multi-modal Deep Analysis for Multimedia
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• On Transferability of Prompt Tuning for Natural Language Processing
• Context-Aware Embeddings for Automatic Art Analysis
• Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU
• Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data
• Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate
• ECRECer: Enzyme Commission Number Recommendation and Benchmarking based on Multiagent Dual-core Learning
• Reflective Fiber Faults Detection and Characterization Using Long-Short-Term Memory
• MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction
• Synergic Adversarial Label Learning for Grading Retinal Diseases via Knowledge Distillation and Multi-task Learning
• Understanding and Improving Information Transfer in Multi-Task Learning
• MetaBalance: Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks
• A neural network walks into a lab: towards using deep nets as models for human behavior
• Light Field Image Quality Assessment With Auxiliary Learning Based on Depthwise and Anglewise Separable Convolutions
• Underwater-Art: Expanding Information Perspectives With Text Templates For Underwater Acoustic Target Recognition
• Learning to Branch for Multi-Task Learning
• Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning
• Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
• Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets
• Depth Estimation and Image Restoration by Deep Learning from Defocused Images
• 12-in-1: Multi-Task Vision and Language Representation Learning
• FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
• A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
• When Deep Learning Meets Multi-Task Learning in SAR ATR: Simultaneous Target Recognition and Segmentation
• COVID-MTL: Multitask Learning with Shift3D and Random-weighted Loss for Automated Diagnosis and Severity Assessment of COVID-19
• DNN and CNN with Weighted and Multi-task Loss Functions for Audio Event Detection
• A multi-task learning for cavitation detection and cavitation intensity recognition of valve acoustic signals
• Regularizing Deep Multi-Task Networks using Orthogonal Gradients
• Pedestrian Attribute Recognition: A Survey
• Learning the Pareto Front with Hypernetworks
• PADL: Language-Directed Physics-Based Character Control
• DeepFaceLIFT: Interpretable Personalized Models for Automatic Estimation of Self-Reported Pain
• A Novel Temporal Multi-Gate Mixture-of-Experts Approach for Vehicle Trajectory and Driving Intention Prediction
• Heterogeneous Multi-task Learning with Expert Diversity
• Efficiently Identifying Task Groupings for Multi-Task Learning
• Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog
• AuxNet: Auxiliary tasks enhanced Semantic Segmentation for Automated Driving
• Vehicle Attribute Recognition by Appearance: Computer Vision Methods for Vehicle Type, Make and Model Classification
• Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back
• Graph Neural Networks for Surfactant Multi-Property Prediction
• Deep Neural Networks for Marine Debris Detection in Sonar Images
• Controllable Multi-Objective Re-ranking with Policy Hypernetworks
• Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera
• Reducing the Model Variance of a Rectal Cancer Segmentation Network
• Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articles
• Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond
• Attention over Parameters for Dialogue Systems
• EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search
• Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices
• Dynamic Multi-Task Learning for Face Recognition with Facial Expression
• Replay in Deep Learning: Current Approaches and Missing Biological Elements
• M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations
• Controllable Pareto Multi-Task Learning
• Deep Learning for Classification and Severity Estimation of Coffee Leaf Biotic Stress
• Learning Clustered Representation for Complex Free Energy Landscapes
• AutoML4ETC: Automated Neural Architecture Search for Real-World Encrypted Traffic Classification
• Multi-Task Reinforcement Learning with Context-based Representations
• Subtask Gated Networks for Non-Intrusive Load Monitoring
• Multi-Modal Multi-Task (3MT) Road Segmentation
• A Multi-task Learning Framework for Product Ranking with BERT
• Semi-Supervised Sequence Modeling with Cross-View Training
• Multitask Learning for Emotion and Personality Detection
• Extending Unsupervised Neural Image Compression With Supervised Multitask Learning
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
• Where is the Model Looking At?--Concentrate and Explain the Network Attention
• H3DNet: 3D Object Detection Using Hybrid Geometric Primitives
• Sequence Labeling Parsing by Learning Across Representations
• The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning
• Multimodal Multitask Representation Learning for Pathology Biobank Metadata Prediction
• Multitask Learning for Scalable and Dense Multilayer Bayesian Map Inference
• Implicit Model Specialization through DAG-based Decentralized Federated Learning
• DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning
• One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction
• Antipatterns in Software Classification Taxonomies
• Empirical Analysis of Multi-Task Learning for Reducing Model Bias in Toxic Comment Detection
• Zero-shot Domain Adaptation without Domain Semantic Descriptors
• Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set
• Prediction of hierarchical time series using structured regularization and its application to artificial neural networks
• Handling Noisy Labels via One-Step Abductive Multi-Target Learning and Its Application to Helicobacter Pylori Segmentation
• Unified Mandarin TTS Front-end Based on Distilled BERT Model
• Advancing Robust Underwater Acoustic Target Recognition through Multi-task Learning and Multi-Gate Mixture-of-Experts
• A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms
• Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes
• Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties
• Auxiliary Task Reweighting for Minimum-data Learning
• The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding
• Learning Cross-Domain Representation with Multi-Graph Neural Network
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
• A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization
• Personalized Driver Stress Detection with Multi-task Neural Networks using Physiological Signals
• The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneck
• Unified Adversarial Invariance
• Constructing Time-Series Momentum Portfolios with Deep Multi-Task Learning
• Single-Network Whole-Body Pose Estimation
• An Empirical Study of Multi-Task Learning on BERT for Biomedical Text Mining
• Explainable AI and susceptibility to adversarial attacks: a case study in classification of breast ultrasound images
• Pose Neural Fabrics Search
• Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback
• Multitask Learning for Fundamental Frequency Estimation in Music
• A Deep Probabilistic Model for Customer Lifetime Value Prediction
• A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization
• Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
• Feature Partitioning for Efficient Multi-Task Architectures
• Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
• Exploring and Predicting Transferability across NLP Tasks
• How Important is the Train-Validation Split in Meta-Learning?
• From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining
• Hybrid coarse-fine classification for head pose estimation
• VersatileGait: A Large-Scale Synthetic Gait Dataset with Fine-GrainedAttributes and Complicated Scenarios
• Multi-Task Learning by Deep Collaboration and Application in Facial Landmark Detection
• A Comprehensive Evaluation of Multi-task Learning and Multi-task Pre-training on EHR Time-series Data
• Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting
• Enabling Early Audio Event Detection with Neural Networks
• Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning
• In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems
• Soft Prompt Decoding for Multilingual Dense Retrieval
• The Effect of Heterogeneous Data for Alzheimer's Disease Detection from Speech
• Temporal Attribute Prediction via Joint Modeling of Multi-Relational Structure Evolution
• Generalizing Speaker Verification for Spoof Awareness in the Embedding Space
• Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
• A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learning
• Multi-head Sequence Tagging Model for Grammatical Error Correction
• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
• End-to-end Person Search Sequentially Trained on Aggregated Dataset
• Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
• Meta Reinforcement Learning with Task Embedding and Shared Policy
• EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
• An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models
• Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks
• Attention based end to end Speech Recognition for Voice Search in Hindi and English
• Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation
• Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
• A Cross-Stitch Architecture for Joint Registration and Segmentation in Adaptive Radiotherapy
• Multi-script Handwritten Digit Recognition Using Multi-task Learning
• Attention-Augmented End-to-End Multi-Task Learning for Emotion Prediction from Speech
• Evolutionary Architecture Search For Deep Multitask Networks
• Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning
• Deep Learning Approach for Matrix Completion Using Manifold Learning
• An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection
• Multi-task learning from fixed-wing UAV images for 2D/3D city modeling
• Learning Discriminative features using Center Loss and Reconstruction as Regularizer for Speech Emotion Recognition
• Exploiting All Samples in Low-Resource Sentence Classification: Early Stopping and Initialization Parameters
• Combination of Domain Knowledge and Deep Learning for Sentiment Analysis of Short and Informal Messages on Social Media
• A Multi-task Learning Framework for Drone State Identification and Trajectory Prediction
• Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising
• Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
• Deep learning complete intersection Calabi-Yau manifolds
• Towards a population-informed approach to the definition of data-driven models for structural dynamics
• Aggregating From Multiple Target-Shifted Sources
• The Nash-MTL-STCN Method For Prestack Three-Parameter Inversion
• Topology-Aware Graph Pooling Networks
• Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies
• Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks
• The Natural Language of Actions
• $F$, $B$, Alpha Matting
• Measuring and Harnessing Transference in Multi-Task Learning
• Context Aware Machine Learning
• Predicting the Popularity of Online Videos via Deep Neural Networks
• Closing the gap towards end-to-end autonomous vehicle system
• Small Towers Make Big Differences
• A Brief Review of Deep Multi-task Learning and Auxiliary Task Learning
• DaCy: A Unified Framework for Danish NLP
• SpeechNet: A Universal Modularized Model for Speech Processing Tasks
• Robust Optimization for Multilingual Translation with Imbalanced Data
• On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment
• Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis
• End-to-end Learning Improves Static Object Geo-localization in Monocular Video
• Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
• Stop Illegal Comments: A Multi-Task Deep Learning Approach
• A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification
• Training Complex Models with Multi-Task Weak Supervision
• Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
• Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
• Multi-Label Transfer Learning for Multi-Relational Semantic Similarity
• A Multi-Task Deep Learning Framework for Building Footprint Segmentation
• Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions
• Hierarchical Capsule Prediction Network for Marketing Campaigns Effect
• Two-path Deep Semi-supervised Learning for Timely Fake News Detection
• GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning
• An Open-Source Dataset and A Multi-Task Model for Malay Named Entity Recognition
• Telescoping Density-Ratio Estimation
• CatVRNN: Generating Category Texts via Multi-task Learning
• AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning
• Joint Liver Lesion Segmentation and Classification via Transfer Learning
• Multi-Task Variational Information Bottleneck
• Multi-Task Self-Training for Learning General Representations
• Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral
• HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections
• A Feature Transfer Enabled Multi-Task Deep Learning Model on Medical Imaging
• Asymmetric GANs for Image-to-Image Translation
• Knowledge Distillation for Multi-task Learning
• Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
• Neural Skill Transfer from Supervised Language Tasks to Reading Comprehension
• Outage-Watch: Early Prediction of Outages using Extreme Event Regularizer
• Transfer Learning in the Field of Renewable Energies -- A Transfer Learning Framework Providing Power Forecasts Throughout the Lifecycle of Wind Farms After Initial Connection to the Electrical Grid
• Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension
• Audio-Linguistic Embeddings for Spoken Sentences
• Weakly Supervised Multi-task Learning for Concept-based Explainability
• Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
• Comprehensive and Efficient Data Labeling via Adaptive Model Scheduling
• NeurReg: Neural Registration and Its Application to Image Segmentation
• Multitask Learning for Class-Imbalanced Discourse Classification
• Byzantine Resilient Distributed Multi-Task Learning
• Polarity and Intensity: the Two Aspects of Sentiment Analysis
• Hybrid Model with Time Modeling for Sequential Recommender Systems
• Multi-Agent Reinforcement Learning for Unmanned Aerial Vehicle Coordination by Multi-Critic Policy Gradient Optimization
• Inducing Causal Structure for Interpretable Neural Networks
• Cross-Task Consistency Learning Framework for Multi-Task Learning
• Learning to Transfer for Traffic Forecasting via Multi-task Learning
• Skin disease diagnosis with deep learning: a review
• Deep Bayesian Multi-Target Learning for Recommender Systems
• Towards Better Forecasting by Fusing Near and Distant Future Visions
• Reconfigurable Intelligent Surface-Assisted Aerial-Terrestrial Communications via Multi-Task Learning
• Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection
• DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
• Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields
• Neural MOS Prediction for Synthesized Speech Using Multi-Task Learning With Spoofing Detection and Spoofing Type Classification
• Personalized Federated Learning of Driver Prediction Models for Autonomous Driving
• MultiNet: Multi-Modal Multi-Task Learning for Autonomous Driving
• Meta-Learning with MAML on Trees
• Bridging the gap between target-based and cell-based drug discovery with a graph generative multi-task model
• RotoGrad: Gradient Homogenization in Multitask Learning
• Cell Type Identification from Single-Cell Transcriptomic Data via Semi-supervised Learning
• Multi-speaker Text-to-speech Synthesis Using Deep Gaussian Processes
• Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications
• Named Entities in Medical Case Reports: Corpus and Experiments
• TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
• A Foliated View of Transfer Learning
• Instance-Level Task Parameters: A Robust Multi-task Weighting Framework
• Self-supervised Depth Estimation to Regularise Semantic Segmentation in Knee Arthroscopy
• Learning Multiple Dense Prediction Tasks from Partially Annotated Data
• Multi-Task Learning with Contextualized Word Representations for Extented Named Entity Recognition
• Harvesting the Lyα forest with convolutional neural networks
• DeepCSO: Forecasting of Combined Sewer Overflow at a Citywide Level using Multi-task Deep Learning
• Lossless Compression of Mosaic Images with Convolutional Neural Network Prediction
• What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
• Frosting Weights for Better Continual Training
• Hierarchical Multi-task Deep Neural Network Architecture for End-to-End Driving
• Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
• Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
• Label-efficient audio classification through multitask learning and self-supervision
• Self-supervised learning for fast and scalable time series hyper-parameter tuning
• Multi-task Learning for Multilingual Neural Machine Translation
• Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos
• Hypothesis Disparity Regularized Mutual Information Maximization
• Balance Regularized Neural Network Models for Causal Effect Estimation
• Guitar Effects Recognition and Parameter Estimation with Convolutional Neural Networks
• Multi-Task Deep Learning for Legal Document Translation, Summarization and Multi-Label Classification
• Single Shot Multitask Pedestrian Detection and Behavior Prediction
• It Takes Nine to Smell a Rat: Neural Multi-Task Learning for Check-Worthiness Prediction
• Multilingual Dialogue Generation with Shared-Private Memory
• A Multi-Level Attention Model for Evidence-Based Fact Checking
• A Modularized Neural Network with Language-Specific Output Layers for Cross-lingual Voice Conversion
• A Simple Approach to Continual Learning by Transferring Skill Parameters
• Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes
• Multi-task problems are not multi-objective
• GraftNet: An Engineering Implementation of CNN for Fine-grained Multi-label Task
• Tackling Ordinal Regression Problem for Heterogeneous Data: Sparse and Deep Multi-Task Learning Approaches
• Supervised Contextual Embeddings for Transfer Learning in Natural Language Processing Tasks
• Hyperparameter Transfer Learning with Adaptive Complexity
• Taxonomy Completion via Triplet Matching Network
• Word-Level Loss Extensions for Neural Temporal Relation Classification
• Using dynamic loss weighting to boost improvements in forecast stability
• Exploiting Method Names to Improve Code Summarization: A Deliberation Multi-Task Learning Approach
• Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network
• Generalizing Natural Language Analysis through Span-relation Representations
• TPG-DNN: A Method for User Intent Prediction Based on Total Probability Formula and GRU Loss with Multi-task Learning
• Decision Making Problems with Funnel Structure: A Multi-Task Learning Approach with Application to Email Marketing Campaigns
• M&M: Multimodal-Multitask Model Integrating Audiovisual Cues in Cognitive Load Assessment
• Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity
• Random Polytope Descriptors
• Real-time Multi-Task Diffractive Deep Neural Networks via Hardware-Software Co-design
• Deep Homography Estimation for Dynamic Scenes
• Multi-Task Learning via Co-Attentive Sharing for Pedestrian Attribute Recognition
• I'm Sorry for Your Loss: Spectrally-Based Audio Distances Are Bad at Pitch
• Invariant Feature Learning for Sensor-based Human Activity Recognition
• De-identification of Privacy-related Entities in Job Postings
• Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators
• OCHADAI-KYOTO at SemEval-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction
• Generative Modeling for Multi-task Visual Learning
• Exceeding the Limits of Visual-Linguistic Multi-Task Learning
• Multi-objective optimization and explanation for stroke risk assessment in Shanxi province
• Bert4XMR: Cross-Market Recommendation with Bidirectional Encoder Representations from Transformer
• MetaXT: Meta Cross-Task Transfer between Disparate Label Spaces
• Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
• Augmenting the User-Item Graph with Textual Similarity Models
• Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
• PCA-based Multi Task Learning: a Random Matrix Approach
• MobIE: A German Dataset for Named Entity Recognition, Entity Linking and Relation Extraction in the Mobility Domain
• Training ELECTRA Augmented with Multi-word Selection
• Development of a Multi-Task Learning V-Net for Pulmonary Lobar Segmentation on Computed Tomography and Application to Diseased Lungs
• Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge
• Multi-Task Learning of Query Intent and Named Entities using Transfer Learning
• Network Clustering for Multi-task Learning
• Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark
• Multi-Task Learning for Argumentation Mining
• Semi-supervised Learning for COVID-19 Image Classification via ResNet
• General Purpose Text Embeddings from Pre-trained Language Models for Scalable Inference
• Formant Tracking Using Dilated Convolutional Networks Through Dense Connection with Gating Mechanism
• A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning
• Reducing Overlearning through Disentangled Representations by Suppressing Unknown Tasks
• Directional Multivariate Ranking
• Towards Robust Pattern Recognition: A Review
• Technical Report: Auxiliary Tuning and its Application to Conditional Text Generation
• Deep Multi-Task Learning for Cooperative NOMA: System Design and Principles
• Stock Index Prediction with Multi-task Learning and Word Polarity Over Time
• Learning an Interpretable Graph Structure in Multi-Task Learning
• Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processing
• Privileged Features Distillation at Taobao Recommendations
• Doppler Spectrum Classification with CNNs via Heatmap Location Encoding and a Multi-head Output Layer
• A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling
• Graph-Driven Generative Models for Heterogeneous Multi-Task Learning
• Learning Preference-Based Similarities from Face Images using Siamese Multi-Task CNNs
• ExGate: Externally Controlled Gating for Feature-based Attention in Artificial Neural Networks
• Sim-to-Real Optimization of Complex Real World Mobile Network with Imperfect Information via Deep Reinforcement Learning from Self-play
• FaceLiveNet+: A Holistic Networks For Face Authentication Based On Dynamic Multi-task Convolutional Neural Networks
• From Risk Prediction Models to Risk Assessment Service: A Formulation of Development Paradigm
• Deep Octonion Networks
• Multi-task Learning for Financial Forecasting
• High-Level Perceptual Similarity is Enabled by Learning Diverse Tasks
• Singing voice phoneme segmentation by hierarchically inferring syllable and phoneme onset positions
• Artificial Intelligence for Pediatric Ophthalmology
• 2021 BEETL Competition: Advancing Transfer Learning for Subject Independence & Heterogenous EEG Data Sets
• Basic principles and concept design of a real-time clinical decision support system for managing medical emergencies on missions to Mars
• Neural Random Projection: From the Initial Task To the Input Similarity Problem
• VersatileGait: A Large-Scale Synthetic Gait Dataset Towards in-the-Wild Simulation
• Attention-based multi-task learning for speech-enhancement and speaker-identification in multi-speaker dialogue scenario
• Towards All-around Knowledge Transferring: Learning From Task-irrelevant Labels
• EXMA: A Genomics Accelerator for Exact-Matching
• Multi-task Learning for Human Settlement Extent Regression and Local Climate Zone Classification
• Domain-adaptive Fall Detection Using Deep Adversarial Training
• Self-Supervision based Task-Specific Image Collection Summarization
• Transfer Reinforcement Learning across Homotopy Classes
• Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing
• Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
• Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features
• Dense Fusion Classmate Network for Land Cover Classification
• Leveraging Commonsense Knowledge on Classifying False News and Determining Checkworthiness of Claims
• Harnessing Geometric Constraints from Emotion Labels to improve Face Verification
• Dynamically Modelling Heterogeneous Higher-Order Interactions for Malicious Behavior Detection in Event Logs
• SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis
• On the relationship between multitask neural networks and multitask Gaussian Processes
• Low-Rank Deep Convolutional Neural Network for Multi-Task Learning
• The Bias-Variance Tradeoff of Doubly Robust Estimator with Targeted $L_1$ regularized Neural Networks Predictions
• Towards Dynamic Feature Selection with Attention to Assist Banking Customers in Establishing a New Business
• Distribution Conditional Denoising: A Flexible Discriminative Image Denoiser
• Logically Consistent Loss for Visual Question Answering
• Improve SGD Training via Aligning Mini-batches
• MEETING BOT: Reinforcement Learning for Dialogue Based Meeting Scheduling
• To Schedule or not to Schedule: Extracting Task Specific Temporal Entities and Associated Negation Constraints
• Multi-modal, multi-task, multi-attention (M3) deep learning detection of reticular pseudodrusen: towards automated and accessible classification of age-related macular degeneration
• Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
• A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation
• Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks
• Towards end-to-end pulsed eddy current classification and regression with CNN
• Exploring Correlations in Multiple Facial Attributes through Graph Attention Network
• Learned Image Compression for Machine Perception
• Multi-task Recurrent Neural Networks to Simultaneously Infer Mode and Purpose in GPS Trajectories
• Functionally Modular and Interpretable Temporal Filtering for Robust Segmentation
• Growing Action Spaces
• Improving Multilingual Translation by Representation and Gradient Regularization
• Learning to Transfer: A Foliated Theory
• Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?
• Vision-Guided Forecasting -- Visual Context for Multi-Horizon Time Series Forecasting
• IL-Net: Using Expert Knowledge to Guide the Design of Furcated Neural Networks
• Balancing Average and Worst-case Accuracy in Multitask Learning
• Coded-InvNet for Resilient Prediction Serving Systems
• Multi-task deep-learning optimization of trade-off properties for superior-performance Fe-based soft magnetic alloys
• Fast Line Search for Multi-Task Learning
• Sequence-level self-learning with multiple hypotheses
• Predictive Representation Learning for Language Modeling
• YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker
• Adapting Visual Question Answering Models for Enhancing Multimodal Community Q&A Platforms
• Cooperative Embeddings for Instance, Attribute and Category Retrieval
• Interaction Networks: Using a Reinforcement Learner to train other Machine Learning algorithms
• Lipschitz standardization for multivariate learning
• Improving Multimodal fusion via Mutual Dependency Maximisation
• W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network
• Cross-modal Multi-task Learning for Graphic Recognition of Caricature Face
• A Pose Proposal and Refinement Network for Better Object Pose Estimation
• On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey
• Depth Completion with RGB Prior
• Multi-task Learning for Chinese Word Usage Errors Detection
• Binaural Audio Generation via Multi-task Learning
• Towards Interpretable Multi-Task Learning Using Bilevel Programming
• CALM: Continuous Adaptive Learning for Language Modeling
• Predicting Auditory Spatial Attention from EEG using Single- and Multi-task Convolutional Neural Networks
• Multiple Classification with Split Learning
• Label-Efficient Multi-Task Segmentation using Contrastive Learning
• Multi-task Learning for Low-resource Second Language Acquisition Modeling
• How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements
• Fair Meta-Learning For Few-Shot Classification
• Personalized Attraction Enhanced Sponsored Search with Multi-task Learning