arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.05005cs.LGcs.DC
收藏

基于自适应知识匹配的个性化联邦域增量学习

Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching

School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);Department of Computing, The Hong Kong Polytechnic University(香港理工大学计算学系)

Yichen Li, Wenchao Xu, Haozhao Wang, Ruixuan Li, Yining Qi, Jingcai Guo

AI总结:

针对联邦域增量学习中客户端域偏移问题,提出基于自适应知识匹配的个性化方法 pFedDIL,通过相关性计算选择训练策略并迁移知识,平均准确率最高提升 14.35%。

摘要:

本文聚焦于联邦域增量学习(FDIL),其中每个客户端持续学习增量任务,且各客户端的任务域彼此不同。我们提出了一种新颖的基于自适应知识匹配的个性化联邦域增量学习方法(pFedDIL),该方法允许每个客户端根据与先前任务知识的相关性,交替采用合适的增量任务学习策略。具体而言,当新任务到来时,每个客户端首先计算其与先前任务的本地相关性。然后,客户端可以选择采用新的初始模型或具有相似知识的先前模型来训练新任务,并同时基于这些相关性从先前任务迁移知识。此外,为了识别每个客户端新任务与先前任务之间的相关性,我们分别为每个目标分类模型配备一个辅助分类器,并提出在目标分类模型与辅助分类器之间共享部分参数以压缩模型参数。我们在多个数据集上进行了大量实验,结果表明,就所有任务的平均准确率而言,pFedDIL 相比最先进的方法最高可提升 14.35%。

英文摘要:

This paper focuses on Federated Domain-Incremental Learning (FDIL) where each client continues to learn incremental tasks where their domain shifts from each other. We propose a novel adaptive knowledge matching-based personalized FDIL approach (pFedDIL) which allows each client to alternatively utilize appropriate incremental task learning strategy on the correlation with the knowledge from previous tasks. More specifically, when a new task arrives, each client first calculates its local correlations with previous tasks. Then, the client can choose to adopt a new initial model or a previous model with similar knowledge to train the new task and simultaneously migrate knowledge from previous tasks based on these correlations. Furthermore, to identify the correlations between the new task and previous tasks for each client, we separately employ an auxiliary classifier to each target classification model and propose sharing partial parameters between the target classification model and the auxiliary classifier to condense model parameters. We conduct extensive experiments on several datasets of which results demonstrate that pFedDIL outperforms state-of-the-art methods by up to 14.35\% in terms of average accuracy of all tasks.

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。

↑