Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data

TL;DR

This paper introduces FedWCA, a novel federated learning method for source-free domain adaptation that effectively handles unlabeled data and domain shifts without accessing source data, demonstrating superior performance.

Contribution

The paper proposes FedWCA, a new federated learning approach with weighted cluster aggregation for source-free domain adaptation on unlabeled data, extending prior work from segmentation to classification.

Findings

FedWCA outperforms existing methods in FFREEDA tasks.

The method effectively mitigates domain shifts and privacy issues.

Experimental results validate its practicality and effectiveness.

Abstract

Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this problem, we focus on a source-free domain adaptation task, where (1) the server holds a pre-trained model on labeled source domain data, (2) clients possess only unlabeled data from various target domains, and (3) the server and clients cannot access the source data in the adaptation phase. This task is known as Federated source-Free Domain Adaptation (FFREEDA). Specifically, we focus on classification tasks, while the previous work solely studies semantic segmentation. Our contribution is the novel Federated learning with Weighted Cluster Aggregation (FedWCA) method, designed to mitigate both domain shifts and privacy concerns with only unlabeled data. FedWCA comprises three phases: private and parameter-free clustering of clients to obtain domain-specific global models on the server, weighted aggregation of the global models for the clustered clients, and local domain adaptation with pseudo-labeling. Experimental results show that FedWCA surpasses several existing methods and baselines in FFREEDA, establishing its effectiveness and practicality.