Federated learning with class imbalance reduction
This work aims to improve the convergence performance of federated learning models for practitioners dealing with distributed data and privacy constraints, by mitigating class imbalance.
This paper addresses the slow convergence rate in federated learning caused by class imbalance and unfavorable client selection. It proposes an estimation scheme to reveal class distribution without raw data and a device selection algorithm to minimize class imbalance, which improves the global model's convergence performance.
Federated learning (FL) is a promising technique that enables a large amount of edge computing devices to collaboratively train a global learning model. Due to privacy concerns, the raw data on devices could not be available for centralized server. Constrained by the spectrum limitation and computation capacity, only a subset of devices can be engaged to train and transmit the trained model to centralized server for aggregation. Since the local data distribution varies among all devices, class imbalance problem arises along with the unfavorable client selection, resulting in a slow converge rate of the global model. In this paper, an estimation scheme is designed to reveal the class distribution without the awareness of raw data. Based on the scheme, a device selection algorithm towards minimal class imbalance is proposed, thus can improve the convergence performance of the global model. Simulation results demonstrate the effectiveness of the proposed algorithm.