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=fnbGFH0330
Changes Since Last Submission: We revised our submission based on reviewers' comments, including:
- Add more benchmark results
- Discuss the performance gap between FedIndex and Oracle from a theoretical perspective
- Discuss the heuristic of selection of the balance term, \lambda_d
- Add clarification of DP dataset sensitivity
- Add an intuition illustration on the minimax problem formulation
- Update the hyperparameter table to cover details of joint distritbuion simulation
Assigned Action Editor: ~Sheng_Li3
Submission Number: 7135
Loading