Scalable Strategies for Continual Learning with Replay

• URL: http://arxiv.org/abs/2505.12512v1
• Date: Sun, 18 May 2025 18:23:50 GMT
• Title: Scalable Strategies for Continual Learning with Replay
• Authors: Truman Hickok,
• Abstract summary: We show that replay can play a foundational role in continual learning, allowing models to reconcile new information with past knowledge.<n>In practice, however, replay is quite unscalable, doubling the cost of continual learning when applied naively.<n>We introduce consolidation, a phasic approach to replay which leads to up to 55% less replay samples being needed for a given performance target.<n>Then, we propose sequential merging, an offshoot of task arithmetic which is tailored to the continual learning setting and is shown to work well in combination with replay.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference. This makes continual learning a critical challenge, as methods that efficiently maximize bidirectional transfer across learning trajectories will be essential. Replay is on track to play a foundational role in continual learning, allowing models to directly reconcile new information with past knowledge. In practice, however, replay is quite unscalable, doubling the cost of continual learning when applied naively. Moreover, the continual learning literature has not fully synchronized with the multi-task fine-tuning literature, having not fully integrated highly scalable techniques like model merging and low rank adaptation into a replay-enabled toolset that can produce a unified model in the face of many sequential tasks. In this paper, we begin by applying and analyzing low rank adaptation in a continual learning setting. Next, we introduce consolidation, a phasic approach to replay which leads to up to 55\% less replay samples being needed for a given performance target. Then, we propose sequential merging, an offshoot of task arithmetic which is tailored to the continual learning setting and is shown to work well in combination with replay. Finally, we demonstrate that the developed strategies can operate synergistically, resulting in a highly scalable toolset that outperforms standalone variants.

Related papers

• The Importance of Being Lazy: Scaling Limits of Continual Learning [60.97756735877614]
  We show that increasing model width is only beneficial when it reduces the amount of feature learning, yielding more laziness.<n>We study the intricate relationship between feature learning, task non-stationarity, and forgetting, finding that high feature learning is only beneficial with highly similar tasks.
  arXiv  Detail & Related papers  (2025-06-20T10:12:38Z)
• STAR: Stability-Inducing Weight Perturbation for Continual Learning [4.623295991242981]
  A key challenge in continual learning is that as the model is updated to learn new tasks, it becomes susceptible to catastrophic forgetting.<n>A popular approach to mitigate forgetting during continual learning is to maintain a small buffer of previously-seen samples and to replay them during training.<n>We propose a novel loss function, STAR, that exploits the worst-case parameter perturbation that reduces the KL-divergence of model predictions.
  arXiv  Detail & Related papers  (2025-03-03T14:32:03Z)
• Integrating Curricula with Replays: Its Effects on Continual Learning [3.2489082010225494]
  Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. The goal is to emulate the human learning process, thereby improving knowledge retention and facilitating learning transfer. Existing replay methods in continual learning agents involve the random selection and ordering of data from previous tasks.
  arXiv  Detail & Related papers  (2023-07-08T14:14:55Z)
• PIVOT: Prompting for Video Continual Learning [50.80141083993668]
  We introduce PIVOT, a novel method that leverages extensive knowledge in pre-trained models from the image domain. Our experiments show that PIVOT improves state-of-the-art methods by a significant 27% on the 20-task ActivityNet setup.
  arXiv  Detail & Related papers  (2022-12-09T13:22:27Z)
• 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)
• PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training [94.87393610927812]
  We present an off-policy, interactive reinforcement learning algorithm that capitalizes on the strengths of both feedback and off-policy learning. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods.
  arXiv  Detail & Related papers  (2021-06-09T14:10:50Z)
• Learning Invariant Representation for Continual Learning [5.979373021392084]
  A key challenge in Continual learning is catastrophically forgetting previously learned tasks when the agent faces a new one. We propose a new pseudo-rehearsal-based method, named learning Invariant Representation for Continual Learning (IRCL) Disentangling the shared invariant representation helps to learn continually a sequence of tasks, while being more robust to forgetting and having better knowledge transfer.
  arXiv  Detail & Related papers  (2021-01-15T15:12:51Z)
• Meta-Learning with Sparse Experience Replay for Lifelong Language Learning [26.296412053816233]
  We propose a novel approach to lifelong learning of language tasks based on meta-learning with sparse experience replay. We show that under the realistic setting of performing a single pass on a stream of tasks, our method obtains state-of-the-art results on lifelong text classification and relation extraction.
  arXiv  Detail & Related papers  (2020-09-10T14:36:38Z)
• Importance Weighted Policy Learning and Adaptation [89.46467771037054]
  We study a complementary approach which is conceptually simple, general, modular and built on top of recent improvements in off-policy learning. The framework is inspired by ideas from the probabilistic inference literature and combines robust off-policy learning with a behavior prior. Our approach achieves competitive adaptation performance on hold-out tasks compared to meta reinforcement learning baselines and can scale to complex sparse-reward scenarios.
  arXiv  Detail & Related papers  (2020-09-10T14:16:58Z)
• Bilevel Continual Learning [76.50127663309604]
  We present a novel framework of continual learning named "Bilevel Continual Learning" (BCL) Our experiments on continual learning benchmarks demonstrate the efficacy of the proposed BCL compared to many state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-30T16:00:23Z)
• Bridging the Imitation Gap by Adaptive Insubordination [88.35564081175642]
  We show that when the teaching agent makes decisions with access to privileged information, this information is marginalized during imitation learning. We propose 'Adaptive Insubordination' (ADVISOR) to address this gap. ADVISOR dynamically weights imitation and reward-based reinforcement learning losses during training, enabling on-the-fly switching between imitation and exploration.
  arXiv  Detail & Related papers  (2020-07-23T17:59:57Z)

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.