mlsanityData to 7 Oct 2026

How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition

arXiv 2207.07730 ↗First posted 15 Jul 2022cs.LG cs.AIcited by 27

Not on the map. Why?

Abstract (arXiv)

A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general understanding of the world. Such an agent would require the ability to continually accumulate and build upon its knowledge as it encounters new experiences. Lifelong or continual learning addresses this setting, whereby an agent faces a continual stream of problems and must strive to capture the knowledge necessary for solving each new task it encounters. If the agent is capable of accumulating knowledge in some form of compositional representation, it could then selectively reuse and combine relevant pieces of knowledge to construct novel solutions. Despite the intuitive appeal of this simple idea, the literatures on lifelong learning and compositional learning have proceeded largely separately. In an effort to promote developments that bridge between the two fields, this article surveys their respective research landscapes and discusses existing and future connections between them.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 179 of its 249 references that are in the map. First posted on arXiv 15 Jul 2022.

Builds on

179 of 249 references.

References · 179

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2016Learning without Forgettingcited by 2,465
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  7. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  8. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  9. 2016OpenAI Gymcited by 1,684
  10. 2016Progressive Neural Networkscited by 1,332
  11. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  12. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
38 more
  1. 2017Continual Learning with Deep Generative Replaycited by 1,152
  2. 2018Experience Replay for Continual Learningcited by 1,074
  3. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  4. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  5. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  6. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  7. 2018Overcoming catastrophic forgetting with hard attention to the taskcited by 672
  8. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  9. 2019Three scenarios for continual learningcited by 610
  10. 2019Gradient based sample selection for online continual learningcited by 568
  11. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  12. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
  13. 2016The Option-Critic Architecturecited by 433
  14. 2019Online Continual Learning with Maximally Interfered Retrievalcited by 376
  15. 2015Neural Module Networkscited by 375
  16. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  17. 2020dm_control: Software and Tasks for Continuous Controlcited by 368
  18. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  19. 2021Gradient Projection Memory for Continual Learningcited by 338
  20. 2017Variational Continual Learningcited by 335
  21. 2017FeUdal Networks for Hierarchical Reinforcement Learningcited by 328
  22. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
  23. 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 280
  24. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
  25. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 268
  26. 2019Continual learning with hypernetworkscited by 267
  27. 2018Selective Experience Replay for Lifelong Learningcited by 239
  28. 2019Recurrent Independent Mechanismscited by 219
  29. 2019Compacting, Picking and Growing for Unforgetting Continual Learningcited by 207
  30. 2018Online Structured Laplace Approximations For Overcoming Catastrophic Forgettingcited by 197
  31. 2020Coresets via Bilevel Optimization for Continual Learning and Streamingcited by 191
  32. 2019Meta-Learning Representations for Continual Learningcited by 189
  33. 2019Episodic Memory in Lifelong Language Learningcited by 188
  34. 2020Understanding the Role of Training Regimes in Continual Learningcited by 177
  35. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 158
  36. 2020Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semanticscited by 158
  37. 2019LAMOL: LAnguage MOdeling for Lifelong Language Learningcited by 156
  38. 2020Continual Lifelong Learning in Natural Language Processing: A Surveycited by 152

50 most cited of 179 All 179 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 8; 2025: 7; 2026: 2.

27 papers.

Sort:

By area:

  1. 2024Continual Learning and Catastrophic Forgettingcited by 73
  2. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  3. 2022PIVOT: Prompting for Video Continual Learningcited by 45
  4. 2023Embodied Lifelong Learning for Task and Motion Planningcited by 17
  5. 2023Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challengescited by 17
  6. 2024A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practicescited by 15
  7. 2025Federated Continual Learning: Concepts, Challenges, and Solutionscited by 13
  8. 2023Continual Task Allocation in Meta-Policy Network via Sparse Promptingcited by 11
  9. 2025Self-Composing Policies for Scalable Continual Reinforcement Learningcited by 10
  10. 2025Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learningcited by 8
  11. 2023DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensorscited by 7
  12. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 7
15 more
  1. 2025How Does RL Post-training Induce Skill Composition? A Case Study on Countdowncited by 6
  2. 2023Robotic Manipulation Datasets for Offline Compositional Reinforcement Learningcited by 5
  3. 2023Studying Generalization on Memory-Based Methods in Continual Learningcited by 3
  4. 2024Composing Diffusion Policies for Few-shot Learning of Movement Trajectoriescited by 3
  5. 2023Continual Visual Reinforcement Learning with A Life-Long World Modelcited by 2
  6. 2024Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsalcited by 2
  7. 2024CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Buildingcited by 2
  8. 2025An Energy-Based Mechanism for Compositional Behaviorcited by 2
  9. 2026MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learningcited by 2
  10. 2026Sparse Adapter Fusion for Continual Learning in NLPcited by 1
  11. 2023Modularity Trumps Invariance for Compositional Robustnesscited by 0
  12. 2024PAGE: Domain-Incremental Adaptation with Past-Agnostic Generative Replay for Smart Healthcarecited by 0
  13. 2024Distributed Continual Learningcited by 0
  14. 2025Compositional Instruction Following with Language Models and Reinforcement Learningcited by 0
  15. 2025Neural network task specialization via domain constrainingcited by 0