Multi-Task Model Personalization for Federated Supervised SVM in Heterogeneous Networks
This work addresses the challenge of accelerating federated learning for heterogeneous networks, which is incremental as it builds on existing multi-task and ADMM approaches.
The paper tackles the problem of slow convergence in federated learning with heterogeneous devices by proposing an ADMM-based method for SVM classification and regression, achieving efficient training and model personalization for non-i.i.d. data while enhancing privacy with a random mask procedure.
Federated systems enable collaborative training on highly heterogeneous data through model personalization, which can be facilitated by employing multi-task learning algorithms. However, significant variation in device computing capabilities may result in substantial degradation in the convergence rate of training. To accelerate the learning procedure for diverse participants in a multi-task federated setting, more efficient and robust methods need to be developed. In this paper, we design an efficient iterative distributed method based on the alternating direction method of multipliers (ADMM) for support vector machines (SVMs), which tackles federated classification and regression. The proposed method utilizes efficient computations and model exchange in a network of heterogeneous nodes and allows personalization of the learning model in the presence of non-i.i.d. data. To further enhance privacy, we introduce a random mask procedure that helps avoid data inversion. Finally, we analyze the impact of the proposed privacy mechanisms and participant hardware and data heterogeneity on the system performance.