{"ID":2845791,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.05593","arxiv_id":"2511.05593","title":"Gradient Projection onto Historical Descent Directions for Communication-Efficient Federated Learning","abstract":"Federated Learning (FL) enables decentralized model training across multiple clients while optionally preserving data privacy. However, communication efficiency remains a critical bottleneck, particularly for large-scale models. In this work, we introduce two complementary algorithms: ProjFL, designed for unbiased compressors, and ProjFL+EF, tailored for biased compressors through an Error Feedback mechanism. Both methods rely on projecting local gradients onto a shared client-server subspace spanned by historical descent directions, enabling efficient information exchange with minimal communication overhead. We establish convergence guarantees for both algorithms under strongly convex, convex, and non-convex settings. Empirical evaluations on standard FL classification benchmarks with deep neural networks show that ProjFL and ProjFL+EF achieve accuracy comparable to existing baselines while substantially reducing communication costs.","short_abstract":"Federated Learning (FL) enables decentralized model training across multiple clients while optionally preserving data privacy. However, communication efficiency remains a critical bottleneck, particularly for large-scale models. In this work, we introduce two complementary algorithms: ProjFL, designed for unbiased comp...","url_abs":"https://arxiv.org/abs/2511.05593","url_pdf":"https://arxiv.org/pdf/2511.05593v1","authors":"[\"Arnaud Descours\",\"Léonard Deroose\",\"Jan Ramon\"]","published":"2025-11-05T13:11:30Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.NE\",\"math.OC\",\"math.ST\"]","methods":"[]","has_code":false}