mlsanityData to 14 Oct 2026

How to train your MAML

arXiv 1810.09502 ↗First posted 22 Oct 2018cs.LG stat.MLcited by 309

Not on the map. Why?

Abstract (arXiv)

The field of few-shot learning has recently seen substantial advancements. Most of these advancements came from casting few-shot learning as a meta-learning problem. Model Agnostic Meta Learning or MAML is currently one of the best approaches for few-shot learning via meta-learning. MAML is simple, elegant and very powerful, however, it has a variety of issues, such as being very sensitive to neural network architectures, often leading to instability during training, requiring arduous hyperparameter searches to stabilize training and achieve high generalization and being very computationally expensive at both training and inference times. In this paper, we propose various modifications to MAML that not only stabilize the system, but also substantially improve the generalization performance, convergence speed and computational overhead of MAML, which we call MAML++.

Key facts. Cited by 309 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 75; 2022: 89; 2023: 75; 2024: 31; 2025: 29; 2026: 10.

309 papers.

Sort:

By area:

  1. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  2. 2021Meta-learning via Language Model In-context Tuningcited by 164
  3. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 153
  4. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  5. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 130
  6. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 127
  7. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  8. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 88
  9. 2022Few-Shot Preference Learning for Human-in-the-Loop RLcited by 87
  10. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  11. 2022Tutorial on amortized optimizationcited by 83
  12. 2022Transformers as Meta-Learners for Implicit Neural Representationscited by 79
38 more
  1. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  2. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  3. 2021MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaptioncited by 65
  4. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  5. 2021Continual Learning via Local Module Compositioncited by 63
  6. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
  7. 2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
  8. 2022HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learningcited by 55
  9. 2021StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrievalcited by 50
  10. 2021Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptationcited by 50
  11. 2022Generalizing to New Physical Systems via Context-Informed Dynamics Modelcited by 50
  12. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  13. 2022FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Contextcited by 49
  14. 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 49
  15. 2023Few-Shot Class-Incremental Learning via Training-Free Prototype Calibrationcited by 46
  16. 2021Bootstrapped Meta-Learningcited by 45
  17. 2023Modeling rapid language learning by distilling Bayesian priors into artificial neural networkscited by 42
  18. 2021How Fine-Tuning Allows for Effective Meta-Learningcited by 41
  19. 2021Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Taskscited by 36
  20. 2021Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentationcited by 36
  21. 2021Meta-Auto-Decoder for Solving Parametric Partial Differential Equationscited by 36
  22. 2022Learning Domain Invariant Prompt for Vision-Language Modelscited by 36
  23. 2021On the Convergence Theory for Hessian-Free Bilevel Algorithmscited by 35
  24. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  25. 2022Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradientscited by 34
  26. 2022Sketch3T: Test-Time Training for Zero-Shot SBIRcited by 34
  27. 2021Rapid Neural Architecture Search by Learning to Generate Graphs from Datasetscited by 33
  28. 2021Learning where to learn: Gradient sparsity in meta and continual learningcited by 33
  29. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  30. 2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
  31. 2021Meta-Learning to Improve Pre-Trainingcited by 27
  32. 2024Learning to Defer to a Population: A Meta-Learning Approachcited by 27
  33. 2022Meta Learning for Natural Language Processing: A Surveycited by 26
  34. 2024Prompt Learning via Meta-Regularizationcited by 26
  35. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  36. 2023Mask-guided BERT for Few Shot Text Classificationcited by 25
  37. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  38. 2021Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimizationcited by 23

50 most cited of 309 All 309 (JSON)