arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2307.04417cs.LGcs.CY
收藏

具有收敛保证的公平性感知联邦极小极大优化

Fairness-aware Federated Minimax Optimization with Convergence Guarantee

The Hong Kong University of Science and Technology(香港科技大学)

Gerry Windiarto Mohamad Dunda, Shenghui Song

AI总结:

本文针对联邦学习中的群体公平性问题,提出新算法FFALM,通过在训练目标施加公平性约束并求解极小极大重构,在保证收敛率理论上界的同时,在CelebA和UTKFace数据集上有效提升了模型公平性。

摘要:

联邦学习(FL)因其保护隐私的特性而备受关注。然而,管理用户数据时缺乏自由可能导致群体公平性问题,即模型偏向种族或性别等敏感因素。为解决此问题,本文提出了一种新算法,即带有增广拉格朗日方法的公平联邦平均(FFALM),专门用于解决FL中的群体公平性问题。具体而言,我们在训练目标上施加公平性约束,并求解该约束优化问题的极小极大重构。然后,我们推导了FFALM收敛率的理论上界。在存在严重统计异质性的情况下,FFALM在CelebA和UTKFace数据集上提升公平性的有效性得到了实证验证。

英文摘要:

Federated learning (FL) has garnered considerable attention due to its privacy-preserving feature. Nonetheless, the lack of freedom in managing user data can lead to group fairness issues, where models are biased towards sensitive factors such as race or gender. To tackle this issue, this paper proposes a novel algorithm, fair federated averaging with augmented Lagrangian method (FFALM), designed explicitly to address group fairness issues in FL. Specifically, we impose a fairness constraint on the training objective and solve the minimax reformulation of the constrained optimization problem. Then, we derive the theoretical upper bound for the convergence rate of FFALM. The effectiveness of FFALM in improving fairness is shown empirically on CelebA and UTKFace datasets in the presence of severe statistical heterogeneity.

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。

↑