Federated Learning (FL) is an emerging paradigm in machine learning without
exposing clients' raw data. In practical scenarios with numerous clients,
encouraging fair and efficient client participation in federated learning is of
utmost importance, which is also challenging given the heterogeneity in data
distribution and device properties. Existing works have proposed different
client-selection methods that consider fairness; however, they fail to select
clients with high utilities while simultaneously achieving fair accuracy
levels. In this paper, we propose a fair client-selection approach that unlocks
threefold fairness in federated learning. In addition to having a fair
client-selection strategy, we enforce an equitable number of rounds for client
participation and ensure a fair accuracy distribution over the clients. The
experimental results demonstrate that FedFair^3, in comparison to the
state-of-the-art baselines, achieves 18.15% less accuracy variance on the IID
data and 54.78% on the non-IID data, without decreasing the global accuracy.
Furthermore, it shows 24.36% less wall-clock training time on average.

该研究论文提出了一种在联邦学习中实现三重公平性的公平客户选择方法，通过公平的客户选择策略、公平的参与轮数和客户间的公平准确度分布，与现有技术基准相比，在 IID 数据上减少了 18.15% 的准确率差异，在非 IID 数据上减少了 54.78% 的准确率差异，并且平均训练时间减少了 24.36%。