Federated Learning with Label Distribution Skew via Logits Calibration. (arXiv:2209.00189v1 [cs.LG])

Traditional federated optimization methods perform poorly with heterogeneous
data (ie, accuracy reduction), especially for highly skewed data. In this
paper, we investigate the label distribution skew in FL, where the distribution
of labels varies across clients. First, we investigate the label distribution
skew from a statistical view. We demonstrate both theoretically and empirically
that previous methods based on softmax cross-entropy are not suitable, which
can result in local models heavily overfitting to minority classes and missing
classes. Additionally, we theoretically …

arxiv distribution federated learning learning skew