对比不同聚合策略在异构数据下的表现，找出最优选择。
A Comparative Study of Federated Learning Aggregation Strategies under Homogeneous and Heterogeneous Data Distributions
- 测试多种联邦学习聚合方法在同质与异构数据下的表现。
- 发现聚合策略效果随数据分布变化，无统一最优方案。
- 适合研究联邦学习优化或实际部署的工程师参考。
联邦学习已成为分布式环境中协同机器学习的变革性范式。然而，其性能受服务器端组合本地模型更新的聚合策略显著影响，直接关系到学习效果、鲁棒性及系统行为。本文在同质与异构数据分布下，对广泛使用的联邦聚合策略进行了全面实验对比。基于基准图像分类数据集，分析不同聚合机制在不同程度数据异构性下的表现，考察其对中心化准确率与损失，以及系统级效率指标（包括聚合、训练和通信时间）的影响。结果表明，聚合策略在不同数据集和分布下呈现显著权衡，其有效性取决于数据特征与运行条件。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。