arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.05623cs.LGcs.CV
收藏

连续学习中的无遗忘与正向知识迁移

Continual Learning of Achieving Forgetting-free and Positive Knowledge Transfer

School of Computer Science and Technology, Xidian University(电子科技大学计算机科学与技术学院);Department of Computer Science, University of Illinois at Chicago(伊利诺伊大学芝加哥分校计算机科学系)

Zhi Wang, Zhongbin Wu, Yanni Li, Bing Liu, Guangxi Li, Yuping Wang

AI总结:

本文提出ETCL方法,通过优化策略和正交梯度投影实现无遗忘和正向知识迁移,提升连续学习性能。

摘要:

现有连续学习(CL)研究主要集中在解决灾难性遗忘(CF)问题,以平衡新任务的学习可塑性和旧任务的记忆稳定性。然而,理想的CL代理不仅应克服CF,还应鼓励正向和反向的知识迁移(KT),即使用先前任务学习的知识来学习新任务(即FKT),并利用新任务的知识提升旧任务的性能(即BKT)。为此,本文首先将CL建模为一个优化问题,在此问题中,每个连续学习任务旨在在约束条件下实现最优性能,即FKT和BKT都应为正。然后提出了一种新的增强型任务连续学习(ETCL)方法,实现了无遗忘和正向KT。此外,理论上估计了导致负FKT和BKT的界限。基于这些界限,还提出了一种新的在线任务相似性检测策略,以促进正向KT。为了克服CF,ETCL学习了一组任务特定的二进制掩码,以隔离每个任务的稀疏子网络,同时保持密集网络的性能。在新任务学习开始时,ETCL试图将新任务的梯度与先前最相似任务的子网络梯度对齐,以确保正向FKT。通过使用新的双目标优化策略和正交梯度投影方法,ETCL仅更新分类层上先前相似任务的权重,以实现正向BKT。广泛的评估表明,所提出的ETCL在不相似、相似和混合任务序列上显著优于强大的基线方法。

英文摘要:

Existing research on continual learning (CL) of a sequence of tasks focuses mainly on dealing with catastrophic forgetting (CF) to balance the learning plasticity of new tasks and the memory stability of old tasks. However, an ideal CL agent should not only be able to overcome CF, but also encourage positive forward and backward knowledge transfer (KT), i.e., using the learned knowledge from previous tasks for the new task learning (namely FKT), and improving the previous tasks' performance with the knowledge of the new task (namely BKT). To this end, this paper first models CL as an optimization problem in which each sequential learning task aims to achieve its optimal performance under the constraint that both FKT and BKT should be positive. It then proposes a novel Enhanced Task Continual Learning (ETCL) method, which achieves forgetting-free and positive KT. Furthermore, the bounds that can lead to negative FKT and BKT are estimated theoretically. Based on the bounds, a new strategy for online task similarity detection is also proposed to facilitate positive KT. To overcome CF, ETCL learns a set of task-specific binary masks to isolate a sparse sub-network for each task while preserving the performance of a dense network for the task. At the beginning of a new task learning, ETCL tries to align the new task's gradient with that of the sub-network of the previous most similar task to ensure positive FKT. By using a new bi-objective optimization strategy and an orthogonal gradient projection method, ETCL updates only the weights of previous similar tasks at the classification layer to achieve positive BKT. Extensive evaluations demonstrate that the proposed ETCL markedly outperforms strong baselines on dissimilar, similar, and mixed task sequences.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑