mlsanityData to 7 Oct 2026

Meta-Learning: A Survey

arXiv 1810.03548 ↗First posted 8 Oct 2018cs.LG stat.MLcited by 254

Not on the map. Why?

Abstract (arXiv)

Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible. Not only does this dramatically speed up and improve the design of machine learning pipelines or neural architectures, it also allows us to replace hand-engineered algorithms with novel approaches learned in a data-driven way. In this chapter, we provide an overview of the state of the art in this fascinating and continuously evolving field.

Key facts. Cited by 254 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 73; 2022: 76; 2023: 45; 2024: 22; 2025: 24; 2026: 12.

254 papers.

Sort:

By area:

  1. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  4. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  5. 2021A Survey on Deep Semi-supervised Learningcited by 250
  6. 2021Trustworthy AI: From Principles to Practicescited by 206
  7. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  8. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  9. 2022Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modelingcited by 126
  10. 2025REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewardscited by 121
  11. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  12. 2021Machine Learning with a Reject Option: A surveycited by 107
38 more
  1. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 85
  2. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  3. 2022πBO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimizationcited by 69
  4. 2021Continual Learning via Local Module Compositioncited by 61
  5. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 57
  6. 2024Beyond Model Adaptation at Test Time: A Surveycited by 55
  7. 2021A Survey of Machine Learning for Computer Architecture and Systemscited by 53
  8. 2021Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptationcited by 50
  9. 2020Provable Representation Learning for Imitation Learning via Bi-level Optimizationcited by 41
  10. 2021Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Taskscited by 36
  11. 2021Continual Learning for Recurrent Neural Networks: an Empirical Evaluationcited by 34
  12. 2021Exploiting Adapters for Cross-lingual Low-resource Speech Recognitioncited by 33
  13. 2022Image Coding for Machines with Omnipotent Feature Learningcited by 31
  14. 2022A computational framework for physics-informed symbolic regression with straightforward integration of domain knowledgecited by 31
  15. 2024Quantum Architecture Search: A Surveycited by 31
  16. 2022A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biasescited by 30
  17. 2021Artificial Intelligence in Drug Discovery: Applications and Techniquescited by 28
  18. 2022Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluationcited by 26
  19. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  20. 2021VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decompositioncited by 25
  21. 2021Towards Green Automated Machine Learning: Status Quo and Future Directionscited by 25
  22. 2019Federated Imitation Learning: A Novel Framework for Cloud Robotic Systems with Heterogeneous Sensor Datacited by 24
  23. 2021Formalizing the Generalization-Forgetting Trade-off in Continual Learningcited by 24
  24. 2023Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Modelscited by 24
  25. 2021A deep learning theory for neural networks grounded in physicscited by 23
  26. 2021Meta-Adaptive Nonlinear Control: Theory and Algorithmscited by 23
  27. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  28. 2022Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detectioncited by 23
  29. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  30. 2022Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcited by 22
  31. 2021A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Appscited by 21
  32. 2021Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problemscited by 20
  33. 2021Fairness-Aware Online Meta-learningcited by 19
  34. 2021TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RLcited by 18
  35. 2022Leaving No One Behind: A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modelingcited by 18
  36. 2022Toward Unsupervised Outlier Model Selectioncited by 18
  37. 2021On Data Efficiency of Meta-learningcited by 16
  38. 2022Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019cited by 16

50 most cited of 254 All 254 (JSON)