系统评估联邦学习中非独立同分布数据的影响，发现标签与时空偏移最致命。
A Thorough Assessment of the Non-IID Data Impact in Federated Learning
- 用海林格距离量化客户端间数据分布差异，全面测试四类非独立同分布类型。
- 在特定海林格距离阈值下，模型性能显著下降，极端非独立同分布影响最严重。
- 首次揭示时空偏移对联邦学习的显著影响，为研究者提供关键参考。
联邦学习（FL）允许多个分散客户端在保护数据隐私的前提下协作训练机器学习模型。然而，其去中心化特性导致数据分布非独立同分布（non-IID），进而引发模型性能下降和收敛速度变慢等严重问题。尽管该问题至关重要，但针对各类数据异质性（即非独立同分布性）的系统性实验研究仍十分匮乏。本文通过严谨的实证分析，填补这一空白：采用海林格距离（Hellinger Distance, HD）衡量客户端间分布差异，对比四种前沿方法应对标签、特征、数量及时空偏移等非独立同分布情形，在真实且可控条件下进行基准测试。本研究首次全面分析了联邦学习中的时空偏移效应。结果表明，标签与时空偏移型非独立同分布对模型性能影响最为显著，且在特定海林格距离阈值处出现明显性能跌落；当非独立同分布程度极端时，模型表现受严重影响。研究为未来联邦学习应对数据异质性提供了有效建议，是目前最全面的非独立同分布性分析工作，奠定了坚实的研究基础。
原文摘要 · Abstract (English)
Federated learning (FL) allows collaborative machine learning (ML) model training among decentralized clients' information, ensuring data privacy. The decentralized nature of FL deals with non-independent and identically distributed (non-IID) data. This open problem has notable consequences, such as decreased model performance and more significant convergence times. Despite its importance, experimental studies systematically addressing all types of data heterogeneity (a.k.a. non-IIDness) remain scarce. We aim to fill this gap by assessing and quantifying the non-IID effect through a thorough empirical analysis. We use the Hellinger Distance (HD) to measure differences in distribution among clients. Our study benchmarks four state-of-the-art strategies for handling non-IID data, including label, feature, quantity, and spatiotemporal skewness, under realistic and controlled conditions. This is the first comprehensive analysis of the spatiotemporal skew effect in FL. Our findings highlight the significant impact of label and spatiotemporal skew non-IID types on FL model performance, with notable performance drops occurring at specific HD thresholds. Additionally, the FL performance is heavily affected mainly when the non-IIDness is extreme. Thus, we provide recommendations for FL research to tackle data heterogeneity effectively. Our work represents the most extensive examination of non-IIDness in FL, offering a robust foundation for future research.
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。