A Comprehensive Overview and Survey of Recent Advances in Meta-Learning

Abstract

This article reviews meta-learning also known as learning-to-learn which seeks rapid and accurate model adaptation to unseen tasks with applications in highly automated AI, few-shot learning, natural language processing and robotics. Unlike deep learning, meta-learning can be applied to few-shot high-dimensional datasets and considers further improving model generalization to unseen tasks. Deep learning is focused upon in-sample prediction and meta-learning concerns model adaptation for out-of-sample prediction. Meta-learning can continually perform self-improvement to achieve highly autonomous AI. Meta-learning may serve as an additional generalization block complementary for original deep learning model. Meta-learning seeks adaptation of machine learning models to unseen tasks which are vastly different from trained tasks. Meta-learning with coevolution between agent and environment provides solutions for complex tasks unsolvable by training from scratch. Meta-learning methodology covers a wide range of great minds and thoughts. We briefly introduce meta-learning methodologies in the following categories: black-box meta-learning, metric-based meta-learning, layered meta-learning and Bayesian meta-learning framework. Recent applications concentrate upon the integration of meta-learning with other machine learning framework to provide feasible integrated problem solutions. We briefly present recent meta-learning advances and discuss potential future research directions.

References in corpus (44)

• Continuous control with deep reinforcement learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• ADADELTA: An Adaptive Learning Rate Method
• Prototypical Networks for Few-shot Learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
• Designing Neural Network Architectures using Reinforcement Learning
• Gradient-based Hyperparameter Optimization through Reversible Learning
• Learning to reinforcement learn
• TADAM: Task dependent adaptive metric for improved few-shot learning
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Unsupervised Learning via Meta-Learning
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• Towards a Neural Statistician
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
• Learned Optimizers that Scale and Generalize
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Causal Reasoning from Meta-reinforcement Learning
• Stein Variational Policy Gradient
• Some Considerations on Learning to Explore via Meta-Reinforcement Learning
• Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model
• Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer
• Improving Generalization in Meta Reinforcement Learning using Learned Objectives
• Unsupervised Meta-Learning for Reinforcement Learning
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
• TACO: Learning Task Decomposition via Temporal Alignment for Control
• On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
• Auto-Meta: Automated Gradient Based Meta Learner Search
• Supervising Unsupervised Learning
• Shallow Updates for Deep Reinforcement Learning
• Goedel Machines: Self-Referential Universal Problem Solvers Making Provably Optimal Self-Improvements
• MetaPix: Few-Shot Video Retargeting
• Differentially Private Meta-Learning
• One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL
• Meta-learning curiosity algorithms
• Watch, Try, Learn: Meta-Learning from Demonstrations and Reward
• Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
• Boosting Few-Shot Learning With Adaptive Margin Loss
• Meta-Amortized Variational Inference and Learning
• Learning to Learn Neural Networks

Cited by in corpus (5)

• Learning from similarity and information extraction from structured documents
• A Brief Survey of Associations Between Meta-Learning and General AI
• A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning
• EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications
• Next-item Recommendations in Short Sessions