mlsanityData to 14 Oct 2026

Bayesian Model-Agnostic Meta-Learning

arXiv 1806.03836 ↗First posted 11 Jun 2018cs.LG stat.MLcited by 194

Not on the map. Why?

Abstract (arXiv)

Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with nonparametric variational inference in a principled probabilistic framework. During fast adaptation, the method is capable of learning complex uncertainty structure beyond a point estimate or a simple Gaussian approximation. In addition, a robust Bayesian meta-update mechanism with a new meta-loss prevents overfitting during meta-update. Remaining an efficient gradient-based meta-learner, the method is also model-agnostic and simple to implement. Experiment results show the accuracy and robustness of the proposed method in various tasks: sinusoidal regression, image classification, active learning, and reinforcement learning.

Key facts. Cited by 194 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 66; 2022: 45; 2023: 40; 2024: 17; 2025: 19; 2026: 7.

194 papers.

Sort:

By area:

  1. 2021Transformers Can Do Bayesian Inferencecited by 360
  2. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  3. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  4. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 146
  5. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  6. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  7. 2021Relational Embedding for Few-Shot Classificationcited by 74
  8. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  9. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 62
  10. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
  11. 2021Bayesian Learning via Neural Schr"odinger-F"ollmer Flowscited by 56
  12. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
38 more
  1. 2021Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentationcited by 45
  2. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  3. 2023Modeling rapid language learning by distilling Bayesian priors into artificial neural networkscited by 42
  4. 2021Uncertainty-guided Model Generalization to Unseen Domainscited by 41
  5. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 38
  6. 2021Meta-Auto-Decoder for Solving Parametric Partial Differential Equationscited by 36
  7. 2022FedPop: A Bayesian Approach for Personalised Federated Learningcited by 35
  8. 2021Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifiercited by 32
  9. 2021Fast Adaptation with Linearized Neural Networkscited by 32
  10. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  11. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  12. 2025Latent Thought Models with Variational Bayes Inference-Time Computationcited by 25
  13. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  14. 2021Meta-Learning Reliable Priors in the Function Spacecited by 23
  15. 2021Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimizationcited by 23
  16. 2021Fed-ensemble: Improving Generalization through Model Ensembling in Federated Learningcited by 23
  17. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  18. 2021Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platformscited by 22
  19. 2021Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learningcited by 21
  20. 2021Few-Shot Learning with Class Imbalancecited by 18
  21. 2021Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classificationcited by 18
  22. 2021Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approachcited by 18
  23. 2021An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Datasetcited by 18
  24. 2022What Matters For Meta-Learning Vision Regression Tasks?cited by 18
  25. 2021Model-based Meta Reinforcement Learning using Graph Structured Surrogate Modelscited by 17
  26. 2021Sampling with Mirrored Stein Operatorscited by 17
  27. 2022HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworkscited by 17
  28. 2022Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Predictioncited by 17
  29. 2023Recurrent Hypernetworks are Surprisingly Strong in Meta-RLcited by 16
  30. 2021Meta-Learning with Neural Tangent Kernelscited by 15
  31. 2021Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustnesscited by 14
  32. 2021Hierarchical Variational Memory for Few-shot Learning Across Domainscited by 14
  33. 2022The Effect of Diversity in Meta-Learningcited by 14
  34. 2022Meta-Learning Priors for Safe Bayesian Optimizationcited by 14
  35. 2021Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detectioncited by 13
  36. 2022Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?cited by 13
  37. 2023Learning Large-scale Neural Fields via Context Pruned Meta-Learningcited by 13
  38. 2021Non-Gaussian Gaussian Processes for Few-Shot Regressioncited by 12

50 most cited of 194 All 194 (JSON)