HFedCWA: heterogeneous federated learning algorithm based on contribution-weighted aggregation

Abstract

The aim of heterogeneous federated learning (HFL) is to address the issues of data heterogeneity, computational resource disparity, and model generalizability and security in federated learning (FL). To facilitate the collaborative training of data and enhance the predictive performance of models, a heterogeneous federated learning algorithm based on contribution-weighted aggregation (HFedCWA) is proposed in this paper. First, weights are assigned on the basis of the distribution differences and quantities of heterogeneous device data, and a contribution-based weighted aggregation method is introduced to dynamically adjust weights and balance data heterogeneity. Second, personalized strategies based on regularization are formulated for heterogeneous devices with different weights, enabling each device to participate in the overall task in an optimal manner. Differential privacy methods are concurrently utilized in FL training to further enhance the security of the system. Finally, experiments are conducted under various data heterogeneity scenarios using the MNIST and CIFAR10 datasets, and the results demonstrate that the HFedCWA can effectively improve the model’s generalizability ability and adaptability to heterogeneous data, thereby enhancing the overall efficiency and performance of the HFL system.