Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting

arXiv:2302.05049v4 Announce Type: replace
Abstract: Federated Domain Adaptation (FDA) describes the federated learning (FL) setting where source clients and a server work collaboratively to improve the performance of a target client where limited data is available. The domain shift between the source and target domains, coupled with limited data of the target client, makes FDA a challenging problem, e.g., common techniques such as federated averaging and fine-tuning fail due to domain shift and data scarcity. To theoretically understand the problem, …

abstract arxiv auto client cs.lg data domain domain adaptation domains fda federated learning gradient performance projection server shift type work