当前位置: X-MOL 学术arXiv.cs.MA › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Federated Learning with Fair Worker Selection: A Multi-Round Submodular Maximization Approach
arXiv - CS - Multiagent Systems Pub Date : 2021-07-25 , DOI: arxiv-2107.11728
Fengjiao Li, Jia Liu, Bo Ji

In this paper, we study the problem of fair worker selection in Federated Learning systems, where fairness serves as an incentive mechanism that encourages more workers to participate in the federation. Considering the achieved training accuracy of the global model as the utility of the selected workers, which is typically a monotone submodular function, we formulate the worker selection problem as a new multi-round monotone submodular maximization problem with cardinality and fairness constraints. The objective is to maximize the time-average utility over multiple rounds subject to an additional fairness requirement that each worker must be selected for a certain fraction of time. While the traditional submodular maximization with a cardinality constraint is already a well-known NP-Hard problem, the fairness constraint in the multi-round setting adds an extra layer of difficulty. To address this novel challenge, we propose three algorithms: Fair Continuous Greedy (FairCG1 and FairCG2) and Fair Discrete Greedy (FairDG), all of which satisfy the fairness requirement whenever feasible. Moreover, we prove nontrivial lower bounds on the achieved time-average utility under FairCG1 and FairCG2. In addition, by giving a higher priority to fairness, FairDG ensures a stronger short-term fairness guarantee, which holds in every round. Finally, we perform extensive simulations to verify the effectiveness of the proposed algorithms in terms of the time-average utility and fairness satisfaction.

中文翻译:

具有公平工人选择的联邦学习:一种多轮子模块最大化方法

在本文中,我们研究了联邦学习系统中公平的工人选择问题,其中公平作为一种激励机制,鼓励更多的工人参与联邦。考虑到全局模型达到的训练精度作为所选工人的效用,这通常是单调子模函数,我们将工人选择问题表述为具有基数和公平性约束的新的多轮单调子模最大化问题。目标是最大化多轮的时间平均效用,但必须遵守额外的公平要求,即每个工人必须在一定时间内被选中。虽然具有基数约束的传统子模最大化已经是众所周知的 NP-Hard 问题,多轮设置中的公平约束增加了额外的难度。为了应对这一新挑战,我们提出了三种算法:公平连续贪婪(FairCG1 和 FairCG2)和公平离散贪婪(FairDG),所有这些算法在可行时都满足公平性要求。此外,我们证明了在 FairCG1 和 FairCG2 下实现的时间平均效用的非平凡下界。此外,FairDG 通过更加重视公平性,确保了更强的短期公平性保证,在每一轮中都成立。最后,我们进行了广泛的模拟,以验证所提出算法在时间平均效用和公平满意度方面的有效性。公平连续贪婪(FairCG1和FairCG2)和公平离散贪婪(FairDG),所有这些都在可行的情况下满足公平性要求。此外,我们证明了在 FairCG1 和 FairCG2 下实现的时间平均效用的非平凡下界。此外,FairDG 通过更加重视公平性,确保了更强的短期公平性保证,在每一轮中都成立。最后,我们进行了广泛的模拟,以验证所提出算法在时间平均效用和公平满意度方面的有效性。公平连续贪婪(FairCG1和FairCG2)和公平离散贪婪(FairDG),所有这些都在可行的情况下满足公平性要求。此外,我们证明了在 FairCG1 和 FairCG2 下实现的时间平均效用的非平凡下界。此外,FairDG 通过更加重视公平性,确保了更强的短期公平性保证,在每一轮中都成立。最后,我们进行了广泛的模拟,以验证所提出算法在时间平均效用和公平满意度方面的有效性。在每一轮中都成立。最后,我们进行了广泛的模拟,以验证所提出算法在时间平均效用和公平满意度方面的有效性。在每一轮中都成立。最后,我们进行了广泛的模拟,以验证所提出算法在时间平均效用和公平满意度方面的有效性。
更新日期:2021-07-27
down
wechat
bug