{"doi":"10.48550/arxiv.2302.05049","title":"Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting","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, we introduce new metrics that characterize the FDA setting and a theoretical framework with novel theorems for analyzing the performance of server aggregation rules. Further, we propose a novel lightweight aggregation rule, Federated Gradient Projection ($\\texttt{FedGP}$), which significantly improves the target performance with domain shift and data scarcity. Moreover, our theory suggests an $\\textit{auto-weighting scheme}$ that finds the optimal combinations of the source and target gradients. This scheme improves both $\\texttt{FedGP}$ and a simpler heuristic aggregation rule. Extensive experiments verify the theoretical insights and illustrate the effectiveness of the proposed methods in practice.","journal":"arXiv (Cornell University)","year":2023,"id":398481,"datarank":0.10397207708399181,"base_score":0.6931471805599453,"endowment":0.6931471805599453,"self_citation_contribution":0.10397207708399181,"citation_network_contribution":0.0,"self_endowment_contribution":0.10397207708399181,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9526,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1174880,"name":"Yibo Jacky Zhang","orcid":null,"position":1,"is_corresponding":false},{"id":932563,"name":"Oluwasanmi Koyejo","orcid":"0000-0002-4023-419X","position":2,"is_corresponding":false},{"id":1174879,"name":"Enyi Jiang","orcid":null,"position":0,"is_corresponding":true}],"reference_count":0,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T01:19:47.744358Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}