arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.01784cs.LG
收藏

一个支持动态迁移学习的统一元学习框架

A Unified Meta-Learning Framework for Dynamic Transfer Learning

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Jun Wu, Jingrui He

摘要:

迁移学习是指将知识或信息从相关的源任务转移到目标任务。然而,大多数现有的工作假设这两个任务是从一个固定的任务分布采样,从而导致次优性能的动态任务从一个非固定的任务分布在真实的场景。为了弥补这一差距,在本文中,我们研究了一个更现实和更具挑战性的动态任务迁移学习设置,即,源任务和目标任务随着时间的推移而不断发展。我们从理论上表明,在动态目标任务的期望误差可以紧界的源知识和连续分布的任务之间的差异。这一结果促使我们提出一个通用的元学习框架L2 E建模的知识转移的动态任务。它是围绕一个任务引导的元学习问题与一组元对的任务,基于此,我们能够学习的先验模型初始化快速适应最新的目标任务。L2 E具有以下特性:(1)跨动态任务的有效知识转移能力;(2)快速适应新的目标任务;(3)减轻对历史目标任务的灾难性遗忘;以及(4)灵活地结合任何现有的静态迁移学习算法。在不同图像数据集上的大量实验证明了所提出的L2 E框架的有效性。

英文摘要:

Transfer learning refers to the transfer of knowledge or information from a relevant source task to a target task. However, most existing works assume both tasks are sampled from a stationary task distribution, thereby leading to the sub-optimal performance for dynamic tasks drawn from a non-stationary task distribution in real scenarios. To bridge this gap, in this paper, we study a more realistic and challenging transfer learning setting with dynamic tasks, i.e., source and target tasks are continuously evolving over time. We theoretically show that the expected error on the dynamic target task can be tightly bounded in terms of source knowledge and consecutive distribution discrepancy across tasks. This result motivates us to propose a generic meta-learning framework L2E for modeling the knowledge transferability on dynamic tasks. It is centered around a task-guided meta-learning problem with a group of meta-pairs of tasks, based on which we are able to learn the prior model initialization for fast adaptation on the newest target task. L2E enjoys the following properties: (1) effective knowledge transferability across dynamic tasks; (2) fast adaptation to the new target task; (3) mitigation of catastrophic forgetting on historical target tasks; and (4) flexibility in incorporating any existing static transfer learning algorithms. Extensive experiments on various image data sets demonstrate the effectiveness of the proposed L2E framework.

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。

↑