mlsanityData to 7 Oct 2026

Continual Lifelong Learning with Neural Networks: A Review

arXiv 1802.07569 ↗First posted 21 Feb 2018cs.LG q-bio.NC stat.MLcited by 1,313

Not on the map. Why?

Cited by 25 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. Consequently, lifelong learning capabilities are crucial for autonomous agents interacting in the real world and processing continuous streams of information. However, lifelong learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which information becomes incrementally available over time. In this review, we critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting. We discuss well-established and emerging research motivated by lifelong learning factors in biological systems such as structural plasticity, memory replay, curriculum and transfer learning, intrinsic motivation, and multisensory integration.

Key facts. Cited by 1,313 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 216; 2022: 226; 2023: 260; 2024: 203; 2025: 194; 2026: 214.

1,313 papers.

Sort:

By area:

  1. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  2. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  3. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  4. 2021Learning to Prompt for Continual Learningcited by 938
  5. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  6. 2022Continual Test-Time Domain Adaptationcited by 520
  7. 2021Fast Model Editing at Scalecited by 491
  8. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  9. 2022A Survey of Machine Unlearningcited by 298
  10. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  11. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  12. 2023Towards Unbounded Machine Unlearningcited by 261
38 more
  1. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  2. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
  3. 2023Class-Incremental Learning: A Surveycited by 209
  4. 2023Model Sparsity Can Simplify Machine Unlearningcited by 206
  5. 2024InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learningcited by 189
  6. 2022Dataset Condensation via Efficient Synthetic-Data Parameterizationcited by 187
  7. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 171
  8. 2023Drive Like a Human: Rethinking Autonomous Driving with Large Language Modelscited by 158
  9. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  10. 2022Fine-tuned Language Models are Continual Learnerscited by 152
  11. 2022A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learningcited by 152
  12. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 140
  13. 2023Understanding Catastrophic Forgetting in Language Models via Implicit Inferencecited by 138
  14. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  15. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 129
  16. 2021Avalanche: an End-to-End Library for Continual Learningcited by 124
  17. 2022StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Modelscited by 123
  18. 2022Class-Incremental Continual Learning into the eXtended DER-versecited by 121
  19. 2022FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learningcited by 120
  20. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  21. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 113
  22. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 112
  23. 2023SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understandingcited by 111
  24. 2022Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning Systemcited by 110
  25. 2023Foundational Models Defining a New Era in Vision: A Survey and Outlookcited by 109
  26. 2023Artificial Intelligence for Digital and Computational Pathologycited by 106
  27. 2023A Definition of Continual Reinforcement Learningcited by 98
  28. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  29. 2023Frontier AI Regulation: Managing Emerging Risks to Public Safetycited by 95
  30. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 92
  31. 2021Preservation of the Global Knowledge by Not-True Distillation in Federated Learningcited by 87
  32. 2021Continual Learning for Text Classification with Information Disentanglement Based Regularizationcited by 86
  33. 2021Continual Learning in the Teacher-Student Setup: Impact of Task Similaritycited by 86
  34. 2023Data Distillation: A Surveycited by 86
  35. 2021RECALL: Replay-based Continual Learning in Semantic Segmentationcited by 83
  36. 2022Continual Learning of Natural Language Processing Tasks: A Surveycited by 83
  37. 2022Continual Pre-Training Mitigates Forgetting in Language and Visioncited by 82
  38. 2021Continual Learning of a Mixed Sequence of Similar and Dissimilar Taskscited by 80

50 most cited of 1,313 All 1,313 (JSON)