Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks

• URL: http://arxiv.org/abs/2606.08447v1
• Date: Sun, 07 Jun 2026 04:27:54 GMT
• Title: Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks
• Abstract summary: Humans and animals can learn continuously, acquiring multiple new memories during active learning before consolidating all of them into long-term storage.<n>Our study further suggests that task-specific information remains resilient to new training but decays gradually as network is trained on new tasks.
• Score: 4.951247283741297
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: One of the critical limitations of artificial neural networks is their lack of ability to continually learn: training on new tasks often leads to interference and forgetting of the previous ones. While several algorithms have been proposed to protect old memories from interference, they are typically applied during or immediately after each new episode of training. In contrast, humans and animals can learn continuously, acquiring multiple new memories during active learning before consolidating all of them into long-term storage. Here we show that multiple new tasks can be trained sequentially before an unsupervised sleep-like replay phase is applied to partially restore performance across all previously learned tasks. Our study further suggests that task-specific information remains resilient to new training but decays gradually as network is trained on new tasks. These findings point to novel principles for developing a broad range of continual learning AI solutions.

Related papers

• Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks [8.939294630058729]
  We study a novel lifelong learning paradigm for neural VRP solvers under continually drifting tasks over learning time steps.<n>We propose Dual Replay with Experience Enhancement (DREE), a general framework to improve learning efficiency and mitigate catastrophic forgetting under such drift.
  arXiv  Detail & Related papers  (2026-01-30T03:37:39Z)
• Learning without Isolation: Pathway Protection for Continual Learning [64.3476595369537]
  Deep networks are prone to catastrophic forgetting during sequential task learning.<n>We propose a novel CL framework, learning without isolation(LwI), where model fusion is formulated as graph matching.<n>Thanks to the sparsity of activation channels in a deep network, LwI can adaptively allocate available pathways for a new task, realizing pathway protection and addressing catastrophic forgetting.
  arXiv  Detail & Related papers  (2025-05-24T07:16:55Z)
• Unsupervised Replay Strategies for Continual Learning with Limited Data [1.0687104237121408]
  We show that introducing a sleep phase significantly enhanced accuracy in models trained with limited data. When a few tasks were trained sequentially, sleep replay rescued previously learned information that had been catastrophically forgetting following new task training. This study highlights the multifaceted role of sleep replay in augmenting learning efficiency and facilitating continual learning in ANNs.
  arXiv  Detail & Related papers  (2024-10-21T16:21:09Z)
• Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal [54.93261535899478]
  In real-world applications, such as robotic control of reinforcement learning, the tasks are changing, and new tasks arise in a sequential order.<n>This situation poses the new challenge of plasticity-stability trade-off for training an agent who can adapt to task changes and retain acquired knowledge.<n>We propose a rehearsal-based continual diffusion model, called Continual diffuser (CoD), to endow the diffuser with the capabilities of quick adaptation (plasticity) and lasting retention (stability)
  arXiv  Detail & Related papers  (2024-09-04T08:21:47Z)
• Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study [68.75670223005716]
  We find that pre-trained language models like BERT have a potential ability to learn sequentially, even without any sparse memory replay. Our experiments reveal that BERT can actually generate high quality representations for previously learned tasks in a long term, under extremely sparse replay or even no replay.
  arXiv  Detail & Related papers  (2023-03-02T09:03:43Z)
• Continual learning benefits from multiple sleep mechanisms: NREM, REM, and Synaptic Downscaling [51.316408685035526]
  Learning new tasks and skills in succession without losing prior learning is a computational challenge for both artificial and biological neural networks. Here, we investigate how modeling three distinct components of mammalian sleep together affects continual learning in artificial neural networks.
  arXiv  Detail & Related papers  (2022-09-09T13:45:27Z)
• Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI [10.374979214803805]
  Catastrophic forgetting describes the phenomenon when a neural network completely forgets previous knowledge when given new information. We propose a novel training algorithm called training by explaining in which we leverage Layer-wise Relevance propagation in order to retain the information a neural network has already learned in previous tasks when training on new data. Our method not only successfully retains the knowledge of old tasks within the neural networks but does so more resource-efficiently than other state-of-the-art solutions.
  arXiv  Detail & Related papers  (2022-05-04T08:00:49Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship [54.73817402934303]
  We propose Experience Continual Replay (ERR), a bi-level learning framework to adaptively tune task-wise to achieve a better stability plasticity' tradeoff. ERR can consistently improve the performance of all baselines and surpass current state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-31T12:05:22Z)
• Latent Space based Memory Replay for Continual Learning in Artificial Neural Networks [0.0]
  We explore the application of latent space based memory replay for classification using artificial neural networks. We are able to preserve good performance in previous tasks by storing only a small percentage of the original data in a compressed latent space version.
  arXiv  Detail & Related papers  (2021-11-26T02:47:51Z)
• Thinking Deeply with Recurrence: Generalizing from Easy to Hard Sequential Reasoning Problems [51.132938969015825]
  We observe that recurrent networks have the uncanny ability to closely emulate the behavior of non-recurrent deep models. We show that recurrent networks that are trained to solve simple mazes with few recurrent steps can indeed solve much more complex problems simply by performing additional recurrences during inference.
  arXiv  Detail & Related papers  (2021-02-22T14:09:20Z)
• Beneficial Perturbation Network for designing general adaptive artificial intelligence systems [14.226973149346886]
  We propose a new type of deep neural network with extra, out-of-network, task-dependent biasing units to accommodate dynamic situations. Our approach is memory-efficient and parameter-efficient, can accommodate many tasks, and achieves state-of-the-art performance across different tasks and domains.
  arXiv  Detail & Related papers  (2020-09-27T01:28:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.