mlsanityData to 7 Oct 2026

Lifelong Learning of Compositional Structures

arXiv 2007.07732 ↗First posted 15 Jul 2020cs.LG stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

A hallmark of human intelligence is the ability to construct self-contained chunks of knowledge and adequately reuse them in novel combinations for solving different yet structurally related problems. Learning such compositional structures has been a significant challenge for artificial systems, due to the combinatorial nature of the underlying search problem. To date, research into compositional learning has largely proceeded separately from work on lifelong or continual learning. We integrate these two lines of work to present a general-purpose framework for lifelong learning of compositional structures that can be used for solving a stream of related tasks. Our framework separates the learning process into two broad stages: learning how to best combine existing components in order to assimilate a novel problem, and learning how to adapt the set of existing components to accommodate the new problem. This separation explicitly handles the trade-off between the stability required to remember how to solve earlier tasks and the flexibility required to solve new tasks, as we show empirically in an extensive evaluation.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 10; 2024: 5; 2025: 3; 2026: 1.

34 papers.

Sort:

By area:

  1. 2021Continual Learning via Local Module Compositioncited by 61
  2. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  3. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  4. 2021DualNet: Continual Learning, Fast and Slowcited by 39
  5. 2022Modular Lifelong Reinforcement Learning via Neural Compositioncited by 39
  6. 2024LeanAgent: Lifelong Learning for Formal Theorem Provingcited by 34
  7. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  8. 2021Optimizing Reusable Knowledge for Continual Learning via Metalearningcited by 24
  9. 2023Task-Aware Information Routing from Common Representation Space in Lifelong Learningcited by 22
  10. 2022CompoSuite: A Compositional Reinforcement Learning Benchmarkcited by 21
  11. 2021Towards Lifelong Learning of End-to-end ASRcited by 20
  12. 2023Embodied Lifelong Learning for Task and Motion Planningcited by 17
22 more
  1. 2023Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challengescited by 17
  2. 2022Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activationcited by 16
  3. 2025A Survey of Continual Reinforcement Learningcited by 16
  4. 2024A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practicescited by 15
  5. 2023Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learningcited by 11
  6. 2023Continual Learning for Predictive Maintenance: Overview and Challengescited by 10
  7. 2023Sharing Lifelong Reinforcement Learning Knowledge via Modulating Maskscited by 10
  8. 2022Entropy-based Stability-Plasticity for Lifelong Learningcited by 8
  9. 2021Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Datacited by 7
  10. 2022SHELS: Exclusive Feature Sets for Novelty Detection and Continual Learning Without Class Boundariescited by 7
  11. 2022Federated Continual Learning to Detect Accounting Anomalies in Financial Auditingcited by 4
  12. 2023Visually Grounded Continual Language Learning with Selective Specializationcited by 4
  13. 2023The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learningcited by 3
  14. 2024Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learningcited by 3
  15. 2024RECAST: Reparameterized, Compact weight Adaptation for Sequential Taskscited by 2
  16. 2022Continual Learning, Fast and Slowcited by 0
  17. 2023Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysiscited by 0
  18. 2023Modularity Trumps Invariance for Compositional Robustnesscited by 0
  19. 2024Distributed Continual Learningcited by 0
  20. 2025Hybrid Learners Do Not Forget: A Brain-Inspired Neuro-Symbolic Approach to Continual Learningcited by 0
  21. 2025Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systemscited by 0
  22. 2026Task diversity produces systematic transfer but inhibits continual reinforcement learningcited by 0