现代信息科技2026，Vol.10Issue(7)：116-120,5.DOI:10.19850/j.cnki.2096-4706.2026.07.023
基于LightFL平台的联邦学习算法对比研究
Comparative Study of Federated Learning Algorithms Based on LightFL Platform
摘要
Abstract
This paper addresses the lack of systematic evaluation of federated learning algorithms in practical applications.Using the lightweight platform LightFL,it compares the performance of 10 mainstream algorithms on the MNIST dataset under two data partitioning methods:IID and Dirichlet Non-IID.In the IID scenario,most algorithms perform well with minimal differences.However,in the highly heterogeneous Dirichlet Non-IID scenario,the robustness of each algorithm is challenged.SCAFFOLD,through its unique client-side bias correction mechanism,effectively mitigates the performance degradation caused by data heterogeneity,demonstrating good robustness.The research shows that the performance of federated learning algorithms is highly dependent on the characteristics of the data distribution.When the data distribution is relatively uniform,simple and efficient algorithms such as FedAvg can be given priority;however,in highly heterogeneous scenarios,algorithms with strong robustness,such as SCAFFOLD,are more reliable choices.These findings provide empirical evidence for the selection of federated learning algorithms in different scenarios and have reference value for their promotion and application.关键词
联邦学习/算法评估/独立同分布/非独立同分布Key words
Federated Learning/algorithm evaluation/independent and identically distributed/non-independent and identically distributed分类
信息技术与安全科学引用本文复制引用
王佳欣,李科宏,刘苏月,魏琦佳,俞乐,王灿..基于LightFL平台的联邦学习算法对比研究[J].现代信息科技,2026,10(7):116-120,5.基金项目
2025年北京信息科技大学大学生创新创业训练计划项目(S202511232139) （S202511232139）
2024年北京信息科技大学"青年骨干教师"支持计划(YBT202450) （YBT202450）
面向青藏高原地区的基于人工智能的天气预报模型开发(S2426030) （S2426030）
2025年北京信息科技大学"星光基金"资助项目(XG2025PT92) （XG2025PT92）
