Meta-learning research

---

|| maml_rl | Meta-RL | learning-to-learn | supervised-reptile | pytorch-maml-rl | metacar | pytorch-meta-optimizer | TCML-tensorflow | awesome-architecture-search | awesome-meta-learning | Meta-Learning-Papers | awesome-NAS | google-research/nasbench | [AlphaX-NASBench101] | paperswithcode: meta-learning | paperswithcode: architecture-search | Awesome-Meta-Learning | Hands-On Meta Learning With Python ||

---

Review papers

---

• A Brief Survey of Associations Between Meta-Learning and General AI
• Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
• Multi-Objective Meta Learning
• Meta-Reinforcement Learning for Adaptive Motor Control in Changing Robot Dynamics and Environments
• CATCH: Context-based Meta Reinforcement Learning for Transferrable Architecture Search
• MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning
• Meta-Graph: Few Shot Link Prediction via Meta Learning | Meta-Graph
• A Survey on Evolutionary Neural Architecture Search
• Meta-Learning in Neural Networks: A Survey
• NAAS: Neural Accelerator Architecture Search
• A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning

---

• A Novel Evolutionary Algorithm for Hierarchical Neural Architecture Search
• Bag of Tricks for Neural Architecture Search
• Generative Adversarial Neural Architecture Search
• NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search

---

• ES-MAML: Simple Hessian-Free Meta Learning
• Meta Reinforcement Learning with Autonomous Inference of Subtask Dependencies
• Learning to Recommend via Meta Parameter Partition
• Learning Meta Model for Zero- and Few-shot Face Anti-spoofing
• Meta Reinforcement Learning from observational data
• Meta Learning for End-to-End Low-Resource Speech Recognition
• Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating
• Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation
• Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning
• Improving Federated Learning Personalization via Model Agnostic Meta Learning
• Meta Learning with Relational Information for Short Sequences
• Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
• MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
• Meta Learning for Task-Driven Video Summarization

---

• Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search (2019)
• EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search (2019)
• Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search (2019)
• Hierarchical Critics Assignment for Multi-agent Reinforcement Learning (2019)
• BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning (2019)
• CESMA: Centralized Expert Supervises Multi-Agents (2019)
• Probabilistic Neural Architecture Search (2019)
• Random Search and Reproducibility for Neural Architecture Search (2019)
• Evaluating the Search Phase of Neural Architecture Search (2019)
• Evolutionary Neural AutoML for Deep Learning (2019)
• AutoQB: AutoML for Network Quantization and Binarization on Mobile Devices (2019)
• Online Meta-Learning (2019)
• NAS-Bench-101: Towards Reproducible Neural Architecture Search (2019)
• Concurrent Meta Reinforcement Learning (2019)
• NoRML: No-Reward Meta Learning (2019)
• Provable Guarantees for Gradient-Based Meta-Learning (2019)
• MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning (2019)
• DetNAS: Neural Architecture Search on Object Detection (2019)
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search (2019)
• ASAP: Architecture Search, Anneal and Prune (2019)
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation (2019)
• Meta-Learning surrogate models for sequential decision making (2019)
• Hierarchical Meta Learning (2019)
• AM-LFS: AutoML for Loss Function Search (2019)
• Meta-Learning with Latent Embedding Optimization (2019) [Code]
• A Survey on Neural Architecture Search (2019)
• NAS-FCOS: Fast Neural Architecture Search for Object Detection (2019)
• Densely Connected Search Space for More Flexible Neural Architecture Search [arxiv] (2019)
• XNAS: Neural Architecture Search with Expert Advice (2019)
• A Study of the Learning Progress in Neural Architecture Search Techniques (2019)
• Sample-Efficient Neural Architecture Search by Learning Action Space (2019)
• Scalable Neural Architecture Search for 3D Medical Image Segmentation (2019)
• BayesNAS: A Bayesian Approach for Neural Architecture Search (2019)
• One-Shot Neural Architecture Search via Compressive Sensing (2019)
• V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation (2019)
• A Neural Architecture for Designing Truthful and Efficient Auctions (2019)
• Efficient Novelty-Driven Neural Architecture Search (2019)
• XferNAS: Transfer Neural Architecture Search (2019)
• EPNAS: Efficient Progressive Neural Architecture Search (2019)
• MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning (2019)
• One-Shot Neural Architecture Search Through A Posteriori Distribution Guided Sampling (2019)
• FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search (2019)
• Towards meta-learning for multi-target regression problems

---

• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
• Meta Reinforcement Learning with Distribution of Exploration Parameters Learned by Evolution Strategies (2018)
• Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications (2018)
• Rethink and Redesign Meta learning (2018)
• Taking Human out of Learning Applications: A Survey on Automated Machine Learning (2018)
• Neural Architecture Search: A Survey (2018)
• SNAS: Stochastic Neural Architecture Search (2018)
• A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search (2018)
• FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search (2018)
• Evolutionary Neural Architecture Search for Image Restoration (2018)
• MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning (2018)
• DSO-NAS (2018)
• Auto-Keras: Efficient Neural Architecture Search with Network Morphism (2018)
• Visual Analytics for Automated Model Discovery (2018)
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search (2018)
• DARTS: Differentiable Architecture Search (2018)
• Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search (2018)
• Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells∗ (2018)
• Meta Learning Deep Visual Words for Fast Video Object Segmentation (2018)
• Representation based and Attention augmented Meta learning (2018)
• Meta-Learning for Semi-Supervised Few-Shot Classification.[paper] ICLR 2018. [code]
• Machine Theory of Mind. [arxiv] (2018).
• Meta-Gradient Reinforcement Learning. [arxiv] (2018).
• Learning a Prior over Intent via Meta-Inverse Reinforcement Learning. [arxiv] (2018).
• Probabilistic Model-Agnostic Meta-Learning. [arxiv] (2018).
• Unsupervised Meta-Learning for Reinforcement Learning. [arxiv](2018).
• Meta Learner with Linear Nulling. [arxiv] (2018).
• Bayesian Model-Agnostic Meta-Learning. [arxiv] (2018).
• Meta-Reinforcement Learning of Structured Exploration Strategies. [arxiv] (2018).
• Learning to Adapt: Meta-Learning for Model-Based Control. [arxiv] (2018).
• Evolved policy gradients. [openai] (2018).
• Learning to Explore with Meta-Policy Gradient. [arxiv] (2018).
• Some considerations on learning to explore via meta-reinforcement learning. [arxiv] (2018).
• Meta-learning with differentiable closed-form solvers. [arxiv] (2018).
• Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace. [arxiv] ICML 2018.
• MnasNet: Platform-Aware Neural Architecture Search for Mobile

---

• Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions. [arxiv] (2017).
• Learning to learn by gradient descent by gradient descent. [arxiv] , 2016, [code]
• Using fast weights to attend to the recent past. [arxiv] 2016
• Hypernetworks. In ICLR 2017, [arxiv] .
• Siamese neural networks for one-shot image recognition. [arxiv]
• One-shot learning by inverting a compositional causal process.[arxiv] 2013.
• Meta-learning with memory-augmented neural networks.[arxiv] 2016.
• Matching networks for one shot learning.[arxiv] 2016.
• Learning to remember rare events.[arxiv] In ICLR 2017.
• Learning to navigate in complex environments.[arxiv] DeepMind, 2016.
• Neural architecture search with reinforcement learning. [arxiv] ICLR 2017.
• Rl2: Fast reinforcement learning via slow reinforcement learning. UC Berkeley and OpenAI,[arxiv] 2016.
• Learning to optimize. (ICLR),[arxiv] 2017.
• Towards a neural statistician.[arxiv] (ICLR), 2017.
• Actor-mimic: Deep multitask and transfer reinforcement learning. [arxiv] (ICLR), 2016.
• Optimization as a model for few-shot learning. [arxiv] (ICLR), 2017.
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks.[arxiv] , [code], [pytorch-maml-rl], [code]
• Learning to Learn for Global Optimization of Black Box Functions. [arxiv]
• Meta Networks.[arxiv] 2017.
• One-Shot Imitation Learning.[arxiv] 2017.
• Active One-shot Learning.[arxiv] 2017.
• Learned Optimizers that Scale and Generalize.[arxiv] 2017.
• Low-shot visual object recognition (2016).[arxiv]
• Learning to reinforcement learn.[arxiv] 2016. [code]
• Learning to Learn: Meta-Critic Networks for Sample Efficient Learning. [arxiv] 2017.
• Meta-SGD: Learning to Learn Quickly for Few Shot Learning. [arxiv] 2017.
• Meta-Learning with Temporal Convolutions.[arxiv] 2017. [code]
• Meta Learning Shared Hierarchies.[arxiv] 2017.
• One-shot visual imitation learning via meta-learning. [arxiv] 2017. [code]
• Learning to Compare: Relation Network for Few Shot Learning. [arxiv] 2017.
• Human-level concept learning through probabilistic program induction.[arxiv] 2015.
• Neural task programming: Learning to generalize across hierarchical tasks. [arxiv] 2017.
• Learning feed-forward one-shot learners. [arxiv]
• Learning to learn: Model regression networks for easy small sample learning. [arxiv] 2016.

---

• Meta-learning in reinforcement learning. [paper] 2003.
• Learning to learn using gradient descent. [paper] 2001.
• A meta-learning method based on temporal difference error. [paper] 2009.
• Learning to learn: Introduction and overview. [paper] 1998.
• Meta-learning with backpropagation. [paper] 2001.
• A perspective view and survey of meta-learning. [paper] 2002.
• Zero-data learning of new tasks. [paper] 2008.
• One shot learning of simple visual concepts. [paper] 2011.
• One-shot learning of object categories. [paper] 2006.
• A neural network that embeds its own meta-levels. [paper] 1993.
• Lifelong learning algorithms. [paper] 1998.
• Learning a synaptic learning rule. [paper] 1990.
• On the search for new learning rules for ANNs. [paper] 1995.
• Learning many related tasks at the same time with backpropagation. [paper] 1995.
• Introduction to the special issue on meta-learning. [paper] 2004.
• Meta-learning in computational intelligence. [paper] 2011.
• Fixed-weight networks can learn. [paper] 1990.
• Evolutionary principles in self-referential learning; On learning how to learn: The meta-meta-... hook. [paper] 1987.
• Learning to control fast-weight memories: An alternative to dynamic recurrent networks.Neural Computation, [paper] 1992.
• Simple principles of metalearning. [paper] 1996.
• Learning to learn. [paper] 1998.

---

Maintainer

Gopala KR / @gopala-kr Will