Experience Replay Addresses Loss of Plasticity in Continual Learning

• URL: http://arxiv.org/abs/2503.20018v1
• Date: Tue, 25 Mar 2025 19:01:10 GMT
• Title: Experience Replay Addresses Loss of Plasticity in Continual Learning
• Authors: Jiuqi Wang, Rohan Chandra, Shangtong Zhang,
• Abstract summary: Loss of plasticity is one of the main challenges in continual learning with deep neural networks.<n>We propose a new hypothesis that experience replay addresses the loss of plasticity in continual learning.
• Score: 19.299731724455718
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Loss of plasticity is one of the main challenges in continual learning with deep neural networks, where neural networks trained via backpropagation gradually lose their ability to adapt to new tasks and perform significantly worse than their freshly initialized counterparts. The main contribution of this paper is to propose a new hypothesis that experience replay addresses the loss of plasticity in continual learning. Here, experience replay is a form of memory. We provide supporting evidence for this hypothesis. In particular, we demonstrate in multiple different tasks, including regression, classification, and policy evaluation, that by simply adding an experience replay and processing the data in the experience replay with Transformers, the loss of plasticity disappears. Notably, we do not alter any standard components of deep learning. For example, we do not change backpropagation. We do not modify the activation functions. And we do not use any regularization. We conjecture that experience replay and Transformers can address the loss of plasticity because of the in-context learning phenomenon.

Related papers

• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [93.90047628101155]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks.<n>To address this, some methods propose replaying data from previous tasks during new task learning.<n>However, it is not expected in practice due to memory constraints and data privacy issues.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective [91.14291142262262]
  This work presents a straightforward and fundamental explanation from the data perspective. Our preliminary investigation reveals a strong correlation between the degeneration issue and the presence of repetitions in training data. Our experiments reveal that penalizing the repetitions in training data remains critical even when considering larger model sizes and instruction tuning.
  arXiv  Detail & Related papers  (2023-10-16T09:35:42Z)
• Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages [56.98243487769916]
  Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning. We propose Adaptive RR, which dynamically adjusts the replay ratio based on the critic's plasticity level.
  arXiv  Detail & Related papers  (2023-10-11T12:05:34Z)
• Adiabatic replay for continual learning [138.7878582237908]
  generative replay spends an increasing amount of time just re-learning what is already known. We propose a replay-based CL strategy that we term adiabatic replay (AR) We verify experimentally that AR is superior to state-of-the-art deep generative replay using VAEs.
  arXiv  Detail & Related papers  (2023-03-23T10:18:06Z)
• Loss of Plasticity in Continual Deep Reinforcement Learning [14.475963928766134]
  We demonstrate that deep RL agents lose their ability to learn good policies when they cycle through a sequence of Atari 2600 games. We investigate this phenomenon closely at scale and analyze how the weights, gradients, and activations change over time. Our analysis shows that the activation footprint of the network becomes sparser, contributing to the diminishing gradients.
  arXiv  Detail & Related papers  (2023-03-13T22:37:15Z)
• Detachedly Learn a Classifier for Class-Incremental Learning [11.865788374587734]
  We present an analysis that the failure of vanilla experience replay (ER) comes from unnecessary re-learning of previous tasks and incompetence to distinguish current task from the previous ones. We propose a novel replay strategy task-aware experience replay. Experimental results show our method outperforms current state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-02-23T01:35:44Z)
• New Insights on Reducing Abrupt Representation Change in Online Continual Learning [69.05515249097208]
  We focus on the change in representations of observed data that arises when previously unobserved classes appear in the incoming data stream. We show that applying Experience Replay causes the newly added classes' representations to overlap significantly with the previous classes. We propose a new method which mitigates this issue by shielding the learned representations from drastic adaptation to accommodate new classes.
  arXiv  Detail & Related papers  (2022-03-08T01:37:00Z)
• Reducing Representation Drift in Online Continual Learning [87.71558506591937]
  We study the online continual learning paradigm, where agents must learn from a changing distribution with constrained memory and compute. In this work we instead focus on the change in representations of previously observed data due to the introduction of previously unobserved class samples in the incoming data stream.
  arXiv  Detail & Related papers  (2021-04-11T15:19:30Z)
• Replay in Deep Learning: Current Approaches and Missing Biological Elements [33.20770284464084]
  Replay is the reactivation of one or more neural patterns. It is thought to play a critical role in memory formation, retrieval, and consolidation. We provide the first comprehensive comparison between replay in the mammalian brain and replay in artificial neural networks.
  arXiv  Detail & Related papers  (2021-04-01T15:19:08Z)
• Revisiting Fundamentals of Experience Replay [91.24213515992595]
  We present a systematic and extensive analysis of experience replay in Q-learning methods. We focus on two fundamental properties: the replay capacity and the ratio of learning updates to experience collected.
  arXiv  Detail & Related papers  (2020-07-13T21:22:17Z)
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes [0.0]
  Continual algorithms are designed to accumulate and improve knowledge in a curriculum of learning-experiences without forgetting. Generative Replay consists of regenerating past learning experiences with a generative model to remember them. We show that they are very promising methods for continual learning.
  arXiv  Detail & Related papers  (2020-07-01T13:44:33Z)

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.