Rethinking Transfer in Continual Learning: A Replay-Based Realisation

• URL: http://arxiv.org/abs/2607.15587v1
• Date: Fri, 17 Jul 2026 03:18:17 GMT
• Title: Rethinking Transfer in Continual Learning: A Replay-Based Realisation
• Abstract summary: Continual learning studies how language models can continually acquire new tasks without expensive retraining from scratch.<n>Existing methods, whether rehearsal-based (replaying stored past data) or rehearsal-free (regularising or isolating parameters), overwhelmingly target one objective: preventing catastrophic forgetting.<n>We propose Transfer-Selective Replay (TSR), which selects replay data predicted to benefit the incoming task rather than replaying past examples indiscriminately.
• Score: 14.73400672149583
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch. Existing methods, whether rehearsal-based (replaying stored past data) or rehearsal-free (regularising or isolating parameters), overwhelmingly target one objective: preventing catastrophic forgetting. Forward transfer, the past helping the future, has meanwhile been pursued almost exclusively through parameter reuse, with no explicit account of when transfer should be expected at all. We begin one step earlier: before designing a transfer mechanism, we ask when transfer should exist at all. We answer with a framework of three measurable conditions: the target task must leave room for improvement beyond its own limited supervision, transferable information must survive continued optimisation, and replay must come from compatible previous tasks. We instantiate this view as Transfer-Selective Replay (TSR), which selects replay data predicted to benefit the incoming task rather than replaying past examples indiscriminately. Selection is guided by a zero-training task signature, while distillation preserves stability on previous tasks. Under the standard continual learning protocol in the low-budget regime, TSR consistently improves forward transfer while maintaining stability, outperforming existing replay baselines across heterogeneous and homogeneous task streams. More broadly, the results argue for treating transfer as a first-class objective of continual learning, to be understood before it is engineered.

Related papers

• When to Review: Spaced Repetition for Continual Pre-Training of Language Models [1.0262304700896199]
  Existing replay methods often choose a global old/new mixture and sample uniformly, ignoring that examples differ in how quickly they are forgotten.<n>We formulate continual pre-training as adaptive review scheduling: the training loop should decide not only how much history to replay, but which examples should return at each step.<n>We introduce Spaced Repetition Training (SRT), a continual learning framework inspired by cognitive science, which schedules sample-rehearsal using the SuperMemo-2 (SM-2) algorithm.
  arXiv  Detail & Related papers  (2026-08-18T08:51:47Z)
• Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning [22.058497718429518]
  We propose a replay-free framework that enables controlled backward transfer in prompt-based continual learning.<n>SABER determines when backward refinement is beneficial using complementary task-correlation criteria.<n>Experiments across multiple continual learning benchmarks and diverse pretrained backbones, including T5-Large, LLaMA, and Qwen, demonstrate that SABER consistently achieves positive backward transfer.
  arXiv  Detail & Related papers  (2026-05-31T18:08:24Z)
• Task Switching Without Forgetting via Proximal Decoupling [43.88767637201092]
  In continual learning, the primary challenge is to learn new information without forgetting old knowledge.<n>A common solution addresses this trade-off through regularization, penalizing changes to parameters critical for previous tasks.<n>We propose a different approach that separates task learning from stability enforcement via operator splitting.
  arXiv  Detail & Related papers  (2026-04-20T21:28:13Z)
• SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training [70.84726713548099]
  SAE-based Transferability Score (STS) is a new metric to forecast post-training transferability.<n>We show that STS accurately predicts the transferability of supervised fine-tuning, achieving Pearson correlation coefficients above 0.7 with actual performance changes.
  arXiv  Detail & Related papers  (2026-03-03T12:01:09Z)
• 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)
• Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer [21.57847333976567]
  Multimodal Continual Instruction Tuning (MCIT) enables Multimodal Large Language Models (MLLMs) to meet continuously emerging requirements without expensive retraining. MCIT faces two major obstacles: catastrophic forgetting (where old knowledge is forgotten) and negative forward transfer. We propose Prompt Tuning with Positive Forward Transfer (Fwd-Prompt) to address these issues.
  arXiv  Detail & Related papers  (2024-01-17T12:44:17Z)
• Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
  Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information. We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
  arXiv  Detail & Related papers  (2023-09-15T17:10:51Z)
• Transferability Estimation Based On Principal Gradient Expectation [68.97403769157117]
  Cross-task transferability is compatible with transferred results while keeping self-consistency. Existing transferability metrics are estimated on the particular model by conversing source and target tasks. We propose Principal Gradient Expectation (PGE), a simple yet effective method for assessing transferability across tasks.
  arXiv  Detail & Related papers  (2022-11-29T15:33:02Z)
• 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)
• Unsupervised Transfer Learning for Spatiotemporal Predictive Networks [90.67309545798224]
  We study how to transfer knowledge from a zoo of unsupervisedly learned models towards another network. Our motivation is that models are expected to understand complex dynamics from different sources. Our approach yields significant improvements on three benchmarks fortemporal prediction, and benefits the target even from less relevant ones.
  arXiv  Detail & Related papers  (2020-09-24T15:40:55Z)

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.