Abstract:Federated Learning has emerged as a transformative paradigm for collaborative machine learning across distributed environments. However, its performance is strongly influenced by the aggregation strategy used to combine local model updates at the server, which directly affects learning performance, robustness, and system behavior. This work presents a comprehensive experimental comparison of widely used federated aggregation strategies under both homogeneous and heterogeneous data distributions. Using benchmark image classification datasets, we analyze how different aggregation mechanisms respond to varying degrees of data heterogeneity, examining their impact on centralized accuracy and loss, and system-level efficiency metrics, including aggregation, training, and communication time. The results demonstrate that aggregation strategies exhibit distinct trade-offs across datasets and data distributions, with their effectiveness varying according to dataset characteristics and operating conditions.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.11010 [cs.LG] |
| (or arXiv:2605.11010v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.11010 arXiv-issued DOI via DataCite (pending registration) |
From: Antonios Makris [view email]
[v1]
Sun, 10 May 2026 11:04:30 UTC (312 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。