arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.09095cs.LGcs.CR
收藏

FedSiKD:客户端相似性与知识蒸馏:解决联邦学习中的非独立同分布与约束问题

FedSiKD: Clients Similarity and Knowledge Distillation: Addressing Non-i.i.d. and Constraints in Federated Learning

King Abdulaziz University(阿卜杜勒阿齐兹国王大学);Lun Startup Studio(伦创业工作室);Dhirubhai Ambani Institute of Information and Communication Technology(迪鲁拜·安巴尼信息与通信技术学院);Southern Illinois University at Carbondale(南伊利诺伊大学卡本代尔分校);Riphah International University Islamabad(里法国际大学伊斯兰堡分校)

Yousef Alsenani, Rahul Mishra, Khaled R. Ahmed, Atta Ur Rahman

AI总结:

提出FedSiKD框架,结合客户端相似性与知识蒸馏技术,有效解决联邦学习中的非独立同分布数据与设备约束问题,实现更高精度与更快收敛。

摘要:

近年来,联邦学习(FL)已成为一种以去中心化方式训练机器学习模型同时保护数据隐私的前景广阔的技术。客户端数据的非独立同分布(non-i.i.d.)特性,加上客户端或边缘设备上的约束,给FL带来了重大挑战。此外,跨越大量通信轮次的学习可能存在风险,并可能对模型利用产生潜在的不安全性。传统的FL方法可能会受到这些挑战的影响。因此,我们引入了FedSiKD,它在基于相似性的联邦学习框架中结合了知识蒸馏(KD)。随着客户端加入系统,它们安全地共享关于其数据分布的相关统计信息,促进簇内同质性。这提高了优化效率并加速了学习过程,有效地在教师和学生模型之间转移知识并解决设备约束。FedSiKD通过实现更高的准确率超越了最先进的算法,在HAR和MNIST数据集上,对于$α= {0.1,0.5}$的高度倾斜数据分别超过25%和18%。其更快的收敛速度体现在在HAR和MNIST数据集上,前五轮内准确率分别提高了17%和20%,突显了其早期阶段的学习能力。代码已公开并托管在GitHub上。

英文摘要:

In recent years, federated learning (FL) has emerged as a promising technique for training machine learning models in a decentralized manner while also preserving data privacy. The non-independent and identically distributed (non-i.i.d.) nature of client data, coupled with constraints on client or edge devices, presents significant challenges in FL. Furthermore, learning across a high number of communication rounds can be risky and potentially unsafe for model exploitation. Traditional FL approaches may suffer from these challenges. Therefore, we introduce FedSiKD, which incorporates knowledge distillation (KD) within a similarity-based federated learning framework. As clients join the system, they securely share relevant statistics about their data distribution, promoting intra-cluster homogeneity. This enhances optimization efficiency and accelerates the learning process, effectively transferring knowledge between teacher and student models and addressing device constraints. FedSiKD outperforms state-of-the-art algorithms by achieving higher accuracy, exceeding by 25\% and 18\% for highly skewed data at $α= {0.1,0.5}$ on the HAR and MNIST datasets, respectively. Its faster convergence is illustrated by a 17\% and 20\% increase in accuracy within the first five rounds on the HAR and MNIST datasets, respectively, highlighting its early-stage learning proficiency. Code is publicly available and hosted on GitHub (https://github.com/SimuEnv/FedSiKD)

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。

↑