mlsanityData to 14 Oct 2026

Scalable Recollections for Continual Lifelong Learning

arXiv 1711.06761 ↗First posted 17 Nov 2017cs.LG cs.AI cs.NEcited by 33

Not on the map. Why?

Abstract (arXiv)

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong learning system must have three key capabilities: it must learn and adapt over time, it must not forget what it has learned, and it must be efficient in both training time and memory. Recent techniques have focused their efforts primarily on the first two capabilities while questions of efficiency remain largely unexplored. In this paper, we consider the problem of efficient and effective storage of experiences over very large time-frames. In particular we consider the case where typical experiences are O(n) bits and memories are limited to O(k) bits for k << n. We present a novel scalable architecture and training algorithm in this challenging domain and provide an extensive evaluation of its performance. Our results show that we can achieve considerable gains on top of state-of-the-art methods such as GEM.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 6; 2023: 3; 2024: 8; 2025: 8; 2026: 1.

33 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  2. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 245
  3. 2024Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learningcited by 53
  4. 2024Recent Advances of Multimodal Continual Learning: A Comprehensive Surveycited by 39
  5. 2024Position: Theory of Mind Benchmarks are Broken for Large Language Modelscited by 31
  6. 2022Building a Subspace of Policies for Scalable Continual Learningcited by 28
  7. 2022Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractorcited by 27
  8. 2021Preserving Earlier Knowledge in Continual Learning with the Help of All Previous Feature Extractorscited by 19
  9. 2021Continual Learning In Environments With Polynomial Mixing Timescited by 14
  10. 2024MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuningcited by 14
  11. 2025Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Modelscited by 14
  12. 2022Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2cited by 11
21 more
  1. 2025ProtoDepth: Unsupervised Continual Depth Completion with Prototypescited by 11
  2. 2021IB-DRR: Incremental Learning with Information-Back Discrete Representation Replaycited by 9
  3. 2025ReplayCAD: Generative Diffusion Replay for Continual Anomaly Detectioncited by 9
  4. 2024Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applicationscited by 8
  5. 2022Effects of Auxiliary Knowledge on Continual Learningcited by 7
  6. 2024Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inferencecited by 7
  7. 2025Survey: Multi-Armed Bandits Meet Large Language Modelscited by 7
  8. 2024UnCLe: Benchmarking Unsupervised Continual Learning for Depth Completioncited by 5
  9. 2022System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Gamescited by 3
  10. 2023Continual Visual Reinforcement Learning with A Life-Long World Modelcited by 3
  11. 2025C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisorcited by 3
  12. 2025Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environmentscited by 3
  13. 2021Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescencecited by 2
  14. 2025The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Modelscited by 2
  15. 2026On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Modelscited by 2
  16. 2021Discriminative Distillation to Reduce Class Confusion in Continual Learningcited by 1
  17. 2022Learning Citywide Patterns of Life from Trajectory Monitoringcited by 1
  18. 2023Benchmarking Continual Learning from Cognitive Perspectivescited by 1
  19. 2024Learning Mamba as a Continual Learner: Meta-Learning Selective State Space Models for Continual Learningcited by 1
  20. 2021Etat de l'art sur l'application des bandits multi-brascited by 0
  21. 2025Continual Reinforcement Learning for Cyber-Physical Systems: Lessons Learned and Open Challengescited by 0