Federated Learning on Abhiraj Bibharhttps://abhiraj.pages.dev/tags/federated-learning/Recent content in Federated Learning on Abhiraj BibharHugoenFri, 01 Dec 2023 00:00:00 +0000Toward Reproducible Benchmarks in Federated Learning Researchhttps://abhiraj.pages.dev/publications/reproducible-benchmarks-federated-learning/Fri, 01 Dec 2023 00:00:00 +0000https://abhiraj.pages.dev/publications/reproducible-benchmarks-federated-learning/<h2 id="abstract">Abstract</h2> <p>Federated learning papers frequently report results on incompatible experimental setups — differing client counts, non-IID partitioning strategies, and communication budgets — making cross-paper comparison unreliable. This position paper proposes a minimal standardized benchmark protocol and reports a re-evaluation of six widely cited federated learning methods under matched conditions, finding that reported performance gaps shrink substantially once experimental setup is controlled for.</p>