FedIndex: Federated Domain Adaptation with Continuous Domain Indices

TMLR Paper7135 Authors

Abstract: Federated domain adaptation incorporates source clients’ knowledge to improve the model performance on the target client under the coordination of the server, mitigating the impact of data insufficiency and domain shift. Existing federated domain adaptation (FDA) methods focus on domain adaptation with categorical domain indices (e.g., “source” and “target”), while many real-world tasks involve domains with continuous domain indices. For instance, hospitals need to adapt disease analysis and prediction across patients via age, a continuous domain index in medical applications capturing the underlying relation between patient information and disease analysis. Prior FDA methods struggle with such tasks due to their ignorance of continuous domain indices. This paper proposes FedIndex to enable FDA with continuous domain indices. FedIndex performs adversarial domain adaptation across clients with the help of a global discriminator, aligning all domains’ distributions. Our theoretical analysis demonstrates the capability of FedIndex to generate domain-invariant features across clients using continuous domain indices without accessing data on clients, simultaneously maintaining privacy preservation. Our empirical results show that FedIndex outperforms the state-of-the-art FDA methods on synthetic and real-world datasets.

Submission Type: Long submission (more than 12 pages of main content)

Previous TMLR Submission Url: https://openreview.net/forum?id=lre4ojgM7J

Changes Since Last Submission: We replaced the previously used font style (times) with the default style to make sure it satisfies TMLR's requirements and instructions.

Assigned Action Editor: ~Sheng_Li3

Submission Number: 7135