Auction Based Clustered Federated Learning in Mobile Edge Computing System
This work addresses data heterogeneity and energy efficiency issues for federated learning in mobile edge computing, offering incremental improvements over existing methods.
The paper tackles the problem of data heterogeneity (Non-IID and imbalance) in federated learning within mobile edge computing systems by proposing a cluster-based client selection method to create a federated virtual dataset that approximates the global distribution, and an auction-based scheme within clusters to balance energy consumption and improve convergence, achieving better performance with a CNN model under different data distributions.
In recent years, mobile clients' computing ability and storage capacity have greatly improved, efficiently dealing with some applications locally. Federated learning is a promising distributed machine learning solution that uses local computing and local data to train the Artificial Intelligence (AI) model. Combining local computing and federated learning can train a powerful AI model under the premise of ensuring local data privacy while making full use of mobile clients' resources. However, the heterogeneity of local data, that is, Non-independent and identical distribution (Non-IID) and imbalance of local data size, may bring a bottleneck hindering the application of federated learning in mobile edge computing (MEC) system. Inspired by this, we propose a cluster-based clients selection method that can generate a federated virtual dataset that satisfies the global distribution to offset the impact of data heterogeneity and proved that the proposed scheme could converge to an approximate optimal solution. Based on the clustering method, we propose an auction-based clients selection scheme within each cluster that fully considers the system's energy heterogeneity and gives the Nash equilibrium solution of the proposed scheme for balance the energy consumption and improving the convergence rate. The simulation results show that our proposed selection methods and auction-based federated learning can achieve better performance with the Convolutional Neural Network model (CNN) under different data distributions.