mlsanityData to 7 Oct 2026

Modular meta-learning

arXiv 1806.10166 ↗First posted 26 Jun 2018cs.LG cs.RO stat.MLcited by 51

Not on the map. Why?

Abstract (arXiv)

Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we present a strategy for learning a set of neural network modules that can be combined in different ways. We train different modular structures on a set of related tasks and generalize to new tasks by composing the learned modules in new ways. By reusing modules to generalize we achieve combinatorial generalization, akin to the "infinite use of finite means" displayed in language. Finally, we show this improves performance in two robotics-related problems.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 14; 2023: 9; 2024: 4; 2025: 4; 2026: 2.

51 papers.

Sort:

By area:

  1. 2022The CLRS Algorithmic Reasoning Benchmarkcited by 103
  2. 2023Modular Deep Learningcited by 82
  3. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  4. 2021Wide Neural Networks Forget Less Catastrophicallycited by 64
  5. 2024Combining Induction and Transduction for Abstract Reasoningcited by 53
  6. 2022Modular Lifelong Reinforcement Learning via Neural Compositioncited by 39
  7. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 37
  8. 2021Fast and Slow Learning of Recurrent Independent Mechanismscited by 36
  9. 2022Continual Learning with Recursive Gradient Optimizationcited by 32
  10. 2022Combining Modular Skills in Multitask Learningcited by 27
  11. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  12. 2021Understanding the Dynamics of DNNs Using Graph Modularitycited by 26
38 more
  1. 2021Deep Multi-Task Learning for Joint Localization, Perception, and Predictioncited by 22
  2. 2022CompoSuite: A Compositional Reinforcement Learning Benchmarkcited by 21
  3. 2021Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 20
  4. 2021Transformers with Competitive Ensembles of Independent Mechanismscited by 19
  5. 2023Neural Relational Inference with Fast Modular Meta-learningcited by 16
  6. 2022On the link between conscious function and general intelligence in humans and machinescited by 15
  7. 2023AdaptNet: Policy Adaptation for Physics-Based Character Controlcited by 15
  8. 2021Modular Meta-Learning for Power Control via Random Edge Graph Neural Networkscited by 13
  9. 2021Quantifying Local Specialization in Deep Neural Networkscited by 10
  10. 2022Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewardscited by 10
  11. 2023Mnemosyne: Learning to Train Transformers with Transformerscited by 9
  12. 2021Compositional Learning-based Planning for Vision POMDPscited by 8
  13. 2022On the Generalization and Adaption Performance of Causal Modelscited by 8
  14. 2025Physics of Skill Learningcited by 8
  15. 2025Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMscited by 8
  16. 2021Mixture-of-Variational-Experts for Continual Learningcited by 7
  17. 2022Transfering Hierarchical Structure with Dual Meta Imitation Learningcited by 7
  18. 2023Egocentric Planning for Scalable Embodied Task Achievementcited by 7
  19. 2021Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignmentcited by 6
  20. 2024Breaking Neural Network Scaling Laws with Modularitycited by 5
  21. 2022Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networkscited by 4
  22. 2024MetaFollower: Adaptable Personalized Autonomous Car Followingcited by 4
  23. 2022From Multi-label Learning to Cross-Domain Transfer: A Model-Agnostic Approachcited by 3
  24. 2022Learning Label Modular Prompts for Text Classification in the Wildcited by 3
  25. 2023Modularity in Deep Learning: A Surveycited by 3
  26. 2021Hierarchical Primitive Composition: Simultaneous Activation of Skills with Inconsistent Action Dimensions in Multiple Hierarchiescited by 2
  27. 2021A Simple Approach to Continual Learning by Transferring Skill Parameterscited by 2
  28. 2022Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Divisioncited by 2
  29. 2023Collective Relational Inference for learning heterogeneous interactionscited by 2
  30. 2021Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networkscited by 1
  31. 2023Learning to Compose SuperWeights for Neural Parameter Allocation Searchcited by 1
  32. 2025CARoL: Context-aware Adaptation for Robot Learningcited by 1
  33. 2021Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 0
  34. 2021Meta-learning Amidst Heterogeneity and Ambiguitycited by 0
  35. 2023Meta-Prior: Meta learning for Adaptive Inverse Problem Solverscited by 0
  36. 2024Scalable Multivariate Fronthaul Quantization for Cell-Free Massive MIMOcited by 0
  37. 2025Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systemscited by 0
  38. 2026When Search Becomes Memory: Accelerating Robot Design Discovery with Self-Evolving Skillscited by 0

50 most cited of 51 All 51 (JSON)