Federated learning has attracted increasing attention due to the promise of balancing privacy and large-scale learning; numerous approaches have been proposed. However, most existing approaches focus on problems with balanced data, and prediction performance is far from satisfactory for many real-world applications where the number of samples in different classes is highly imbalanced. To address this challenging problem, we developed a novel federated learning method for imbalanced data by directly optimizing the area under curve (AUC) score. In particular, we formulate the AUC maximization problem as a federated compositional minimax optimization problem, develop a local stochastic compositional gradient descent ascent with momentum algorithm, and provide bounds on the computational and communication complexities of our algorithm. To the best of our knowledge, this is the first work to achieve such favorable theoretical results. Finally, extensive experimental results confirm the efficacy of our method.

翻译：联邦学习因兼顾隐私保护与大规模学习的潜力而备受关注，目前已涌现出大量方法。然而，现有方法多聚焦于平衡数据问题，在面对不同类别样本数量高度不平衡的实际应用场景时，其预测性能远未达到令人满意的水平。为解决这一挑战性问题，我们提出了一种面向不平衡数据的联邦学习方法，通过直接优化曲线下面积（AUC）指标。具体而言，我们将AUC最大化问题建模为联邦组合极小极大优化问题，设计了一种结合动量的局部随机组合梯度下降上升算法，并给出了该算法在计算与通信复杂度上的理论界。据我们所知，这是首个取得如此优异理论成果的工作。最后，大量实验结果验证了本方法的有效性。