Fed-Focal Loss for imbalanced data classification in Federated Learning

Understand

The Federated Learning setting has a central server coordinating the training of a model on a network of devices.

• One of the challenges is variable training performance when the dataset has a class imbalance.
• In this paper, we address this by introducing a new loss function called Fed-Focal Loss.
• We propose to address the class imbalance by reshaping cross-entropy loss such that it down-weights the loss assigned to well-classified examples along the lines of focal loss.