Weakly-Supervised Domain Adaptation in Federated Learning

Enyi Jiang, Oluwasanmi O Koyejo

Keywords: federated learning, domain adaptation, healthcare

TL;DR: We leverage auxiliary information and propose gradient projection (GP) to tackle federated domain adaptation problem under weak supervision.

Abstract: Federated domain adaptation (FDA) describes the setting where a set of source clients seek to optimize the performance of a target client. To be effective, FDA must address some of the distributional challenges of Federated learning (FL). For instance, FL systems exhibit distribution shifts across clients. Further, labeled data are not always available among the clients. To this end, we propose and compare novel approaches for FDA, combining the few labeled target samples with the source data when auxiliary labels are available to the clients. The in-distribution auxiliary information is included during local training to boost out-of-domain accuracy. Also, during fine-tuning, we devise a simple yet efficient gradient projection method to detect the valuable components from each source client model towards the target direction. The extensive experiments on medical imaging datasets show that our proposed framework significantly improves federated domain adaptation performance.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )