提出新框架提升无监督联邦域适应中客户端的标签准确性。
FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation
- 通过服务器与客户端预测对齐，缓解数据异构导致的客户端漂移。
- 在多个视觉数据集上，分类性能超越现有联邦学习方法。
- 适合解决客户端无源域数据、标签未知的联邦学习场景。
本文针对联邦无监督源域自适应（FFreeDA）问题，即客户端持有大量无标签数据且存在显著的跨客户端域差异。由于训练过程中无法访问源域数据集，仅能使用预训练服务器模型，而该源域分布与客户端域差异较大，导致现有方法难以有效适配。传统源域自适应方法在联邦学习中因极端数据异构性引发客户端漂移，产生不可靠伪标签。为此，本文提出FedSCAl框架，引入服务器-客户端对齐（SCAl）机制，通过对齐客户端与服务器模型的预测来正则化客户端更新。实验表明，该机制显著提升了客户端伪标签的准确性，有效缓解了漂移问题。在多个基准视觉数据集上的广泛实验显示，FedSCAl在分类任务中持续优于当前最优联邦学习方法。
原文摘要 · Abstract (English)
We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrains the FL frameworks to employ only a pre-trained server model as the setup restricts access to the source dataset during the training rounds. Often, this source domain dataset has a distinct distribution to the clients' domains. To address the challenges posed by the FFreeDA setup, adaptation of the Source-Free Domain Adaptation (SFDA) methods to FL struggles with client-drift in real-world scenarios due to extreme data heterogeneity caused by the aforementioned domain gaps, resulting in unreliable pseudo-labels. In this paper, we introduce FedSCAl, an FL framework leveraging our proposed Server-Client Alignment (SCAl) mechanism to regularize client updates by aligning the clients' and server model's predictions. We observe an improvement in the clients' pseudo-labeling accuracy post alignment, as the SCAl mechanism helps to mitigate the client-drift. Further, we present extensive experiments on benchmark vision datasets showcasing how FedSCAl consistently outperforms state-of-the-art FL methods in the FFreeDA setup for classification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。