arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.16656cs.LGcs.DC
收藏

Auxo:通过可扩展客户端聚类实现高效联邦学习

Auxo: Efficient Federated Learning via Scalable Client Clustering

University of Michigan(密歇根大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Princeton University(普林斯顿大学);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Southern California(南加州大学)

Jiachen Liu, Fan Lai, Yinwei Dai, Aditya Akella, Harsha Madhyastha, Mosharaf Chowdhury

AI总结:

针对联邦学习中客户端数据非独立同分布导致的收敛慢、精度低等问题,提出Auxo框架,通过可扩展聚类识别数据分布相似的客户端群并自适应训练群专属模型,有效提升了现有联邦学习方案的精度、收敛速度并降低偏差。

摘要:

联邦学习(FL)是一种新兴的机器学习(ML)范式,它使异构边缘设备能够协同训练ML模型,而无需向逻辑集中式服务器泄露其原始数据。然而,除了设备容量异构之外,FL参与者的数据分布通常存在差异,即非独立同分布(Non-IID)。现有许多工作提出了针对性解决方案,以应对FL中由客户端异构性导致的收敛缓慢、最终精度低和存在偏差等问题。本文中,我们探索通过增加一层复杂度来缓解这种异构性,即对数据分布统计相似的客户端进行分组(称为同类群)。我们提出Auxo框架,用于在大规模、低可用性且资源受限的FL群体中逐步识别这类同类群。随后Auxo会自适应确定如何训练同类群专属模型,以实现更优的模型性能并保障资源效率。我们的大量评估表明,通过识别异构性更小的同类群并开展高效的同类群训练,Auxo可提升多种现有FL方案的最终精度(2.1% - 8.2%)、收敛速度(最高2.2倍)并降低模型偏差(4.8% - 53.8%)。

英文摘要:

Federated learning (FL) is an emerging machine learning (ML) paradigm that enables heterogeneous edge devices to collaboratively train ML models without revealing their raw data to a logically centralized server. However, beyond the heterogeneous device capacity, FL participants often exhibit differences in their data distributions, which are not independent and identically distributed (Non-IID). Many existing works present point solutions to address issues like slow convergence, low final accuracy, and bias in FL, all stemming from client heterogeneity. In this paper, we explore an additional layer of complexity to mitigate such heterogeneity by grouping clients with statistically similar data distributions (cohorts). We propose Auxo to gradually identify such cohorts in large-scale, low-availability, and resource-constrained FL populations. Auxo then adaptively determines how to train cohort-specific models in order to achieve better model performance and ensure resource efficiency. Our extensive evaluations show that, by identifying cohorts with smaller heterogeneity and performing efficient cohort-based training, Auxo boosts various existing FL solutions in terms of final accuracy (2.1% - 8.2%), convergence time (up to 2.2x), and model bias (4.8% - 53.8%).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑