Federated Learning (FL) typically aggregates client model parameters using a weighting approach determined by sample proportions. However, this naive weighting method may lead to unfairness and degradation in model performance due to statistical heterogeneity and the inclusion of noisy data among clients. Theoretically, distributional robustness analysis has shown that the generalization performance of a learning model with respect to any shifted distribution is bounded. This motivates us to reconsider the weighting approach in federated learning. In this paper, we replace the aforementioned weighting method with a new strategy that considers the generalization bounds of each local model. Specifically, we estimate the upper and lower bounds of the second-order origin moment of the shifted distribution for the current local model, and then use these bounds disagreements as the aggregation proportions for weightings in each communication round. Experiments demonstrate that the proposed weighting strategy significantly improves the performance of several representative FL algorithms on benchmark datasets.

翻译：联邦学习（FL）通常采用按样本比例确定的加权方法来聚合客户端模型参数。然而，由于客户端间的统计异质性和噪声数据的存在，这种朴素加权方法可能导致不公平性和模型性能退化。从理论上看，分布鲁棒性分析表明，学习模型对任意偏移分布的泛化性能都存在上界。这促使我们重新审视联邦学习中的加权方法。本文用考虑各局部模型泛化界的新策略替代上述加权方法。具体而言，我们估计当前局部模型偏移分布的二阶原点矩的上下界，并将这些界的不一致程度作为每轮通信中聚合权重的分配比例。实验表明，所提出的加权策略显著提升了多种代表性联邦学习算法在基准数据集上的性能。