2025/01/26 by Sunny Gupta, Gupta, Sunny, Vinay Sutar +4 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #C.1.4 #Computer Vision and Pattern Recognition (cs.CV) #D.1.3 #Distributed #FOS: Computer and information sciences #H.3.4 #I.2.10 #I.2.11 #I.2.6 #I.4.0 #I.4.1 #I.4.10 #I.4.2 #I.4.6 #I.4.7 #I.4.8 #I.4.9 #I.5.1 #I.5.2 #I.5.4 #Internet Traffic Analysis and Secure E-voting #J.2 #Machine Learning (cs.LG) #Parallel #Privacy-Preserving Technologies in Data #and Cluster Computing (cs.DC)
paper · pdf · doi:10.48550/arxiv.2501.15486
openalex publication_date 2025/01/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Federated Learning (FL) offers a decentralized paradigm for collaborative model training without direct data sharing, yet it poses unique challenges for Domain Generalization (DG), including strict privacy constraints, non-i.i.d. local data, and limited domain diversity. We introduce FedAlign, a lightweight, privacy-preserving framework designed to enhance DG in federated settings by simultaneously increasing feature diversity and promoting domain invariance. First, a cross-client feature extension module broadens local domain representations through domain-invariant feature perturbation and selective cross-client feature transfer, allowing each client to safely access a richer domain space. Second, a dual-stage alignment module refines global feature learning by aligning both feature embeddings and predictions across clients, thereby distilling robust, domain-invariant features. By integrating these modules, our method achieves superior generalization to unseen domains while maintaining data privacy and operating with minimal computational and communication overhead.