mlsanityData to 14 Oct 2026

Neuromodulated Meta-Learning

arXiv 2411.06746 ↗First posted 11 Nov 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at hrefhttps://github.com/WangJingyao07/NeuronMLhttps://github.com/WangJingyao07/NeuronML.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 61 of its 98 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

61 of 98 references.

References · 61

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  9. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  10. 2019A Closer Look at Few-shot Classificationcited by 684
  11. 2019Meta-Learning with Implicit Gradientscited by 525
  12. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
38 more
  1. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  2. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  3. 2018Meta-learning with differentiable closed-form solverscited by 397
  4. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  5. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  6. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  7. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  8. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  9. 2018Meta-Learning: A Surveycited by 256
  10. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 217
  11. 2019Meta-Learning Representations for Continual Learningcited by 189
  12. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  13. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  14. 2019Online Meta-Learningcited by 137
  15. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  16. 2019Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processescited by 131
  17. 2018Meta-Reinforcement Learning of Structured Exploration Strategiescited by 130
  18. 2019Improved Few-Shot Visual Classificationcited by 115
  19. 2018Meta-Learning Probabilistic Inference For Predictioncited by 110
  20. 2019Meta-Learning without Memorizationcited by 92
  21. 2019Towards Efficient Model Compression via Learned Global Rankingcited by 75
  22. 2015On the Performance of ConvNet Features for Place Recognitioncited by 72
  23. 2017Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithmcited by 65
  24. 2021MT3: Meta Test-Time Training for Self-Supervised Test-Time Adaptioncited by 65
  25. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
  26. 2020Meta-Learning Requires Meta-Augmentationcited by 57
  27. 2020Improving Generalization in Meta-learning via Task Augmentationcited by 55
  28. 2019The Omniglot challenge: a 3-year progress reportcited by 54
  29. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  30. 2021Meta-Learning Sparse Implicit Neural Representationscited by 48
  31. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  32. 2022Efficient Risk-Averse Reinforcement Learningcited by 43
  33. 2022Hypernetworks in Meta-Reinforcement Learningcited by 42
  34. 2020Learning Soft Labels via Meta Learningcited by 27
  35. 2022Meta-Learning Sparse Compression Networkscited by 22
  36. 2020Regularizing Meta-Learning via Gradient Dropoutcited by 15
  37. 2020Meta-Learning with Network Pruningcited by 14
  38. 2023Train Hard, Fight Easy: Robust Meta Reinforcement Learningcited by 12

50 most cited of 61 All 61 (JSON)

Built on by

Not cited yet.