GA Approach to Optimize Training Client Set in Federated Learning
Dongseok Kang, Chang Wook Ahn
Abstract
Federated learning, where the distribution of distributed data is unknown, is more difficult and costly to train a central model with than traditional machine learning. In this study, we propose Federated Learning with Genetic Algorithm, which enables faster central model training at lower cost by providing an appropriate client selection method. A client can have its own communication cost depending on its data sharing preference, and based on this cost and the result of the client’s local update, we can select the appropriate combination of clients each round with a genetic algorithm. In each round, the client’s combinations are evaluated anew, which are continually explored. To evaluate the algorithm, we distributed the image dataset and communication costs in two ways and conducted federated learning for the image classification model. Experiments showed that the proposed algorithm can find a more efficient client combination and accelerate the training of federated learning.