FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation
This addresses domain adaptation in federated learning without access to source data, which is incremental as it builds on existing SFDA methods.
The paper tackles the Federated Source-Free Domain Adaptation problem, where clients have unlabeled data with domain gaps, and shows that FedSCAl improves pseudo-labeling accuracy by aligning client and server predictions, outperforming state-of-the-art methods on benchmark datasets.
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.