arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14937cs.LG
收藏

具有公平平均的联邦学习

Federated Learning with Fair Averaging

Xiamen University(厦门大学);University of Melbourne(墨尔本大学)

Zheng Wang, Xiaoliang Fan, Jianzhong Qi, Chenglu Wen, Cheng Wang, Rongshan Yu

摘要:

公平性已成为联邦学习(FL)中的一个关键问题。在这项工作中,我们确定了FL不公平的原因-冲突的梯度与幅度的巨大差异。为了解决这个问题,我们提出了联邦公平平均(FedFV)算法,以减轻客户端之间的潜在冲突之前,平均其梯度。我们首先使用余弦相似度来检测梯度冲突,然后通过修改梯度的方向和幅度来迭代地消除这种冲突。我们进一步展示了FedFV的理论基础,以减轻冲突的梯度问题,并收敛到帕累托平稳的解决方案。在一组联邦数据集上进行的大量实验证实,FedFV在公平性、准确性和效率方面优于最先进的方法。源代码可在https://github.com/WwZzz/easyFL上获得。

英文摘要:

Fairness has emerged as a critical problem in federated learning (FL). In this work, we identify a cause of unfairness in FL -- conflicting gradients with large differences in the magnitudes. To address this issue, we propose the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradients. We first use the cosine similarity to detect gradient conflicts, and then iteratively eliminate such conflicts by modifying both the direction and the magnitude of the gradients. We further show the theoretical foundation of FedFV to mitigate the issue conflicting gradients and converge to Pareto stationary solutions. Extensive experiments on a suite of federated datasets confirm that FedFV compares favorably against state-of-the-art methods in terms of fairness, accuracy and efficiency. The source code is available at https://github.com/WwZzz/easyFL.

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。

↑