Joint Optimization of Resource Allocation and Data Selection for Fast and Cost-Efficient Federated Edge Learning

TL;DR

This paper proposes a joint optimization framework for resource allocation and data selection in federated edge learning to improve convergence speed and reduce training costs under limited wireless communication resources.

Contribution

It introduces a novel joint optimization approach for resource and data management in FEEL, including problem modeling, transformation, and a low-complexity suboptimal solution.

Findings

The proposed scheme outperforms baseline methods in convergence speed.

The joint optimization reduces overall training costs.

Numerical results validate the effectiveness of the approach.

Abstract

Deploying federated learning at the wireless edge introduces federated edge learning (FEEL). Given FEEL's limited communication resources and potential mislabeled data on devices, improper resource allocation or data selection can hurt convergence speed and increase training costs. Thus, to realize an efficient FEEL system, this paper emphasizes jointly optimizing resource allocation and data selection. Specifically, in this work, through rigorously modeling the training process and deriving an upper bound on FEEL's one-round convergence rate, we establish a problem of joint resource allocation and data selection, which, unfortunately, cannot be solved directly. Toward this end, we equivalently transform the original problem into a solvable form via a variable substitution and then break it into two subproblems, that is, the resource allocation problem and the data selection problem. The two subproblems are mixed-integer non-convex and integer non-convex problems, respectively, and achieving their optimal solutions is a challenging task. Based on the matching theory and applying the convex-concave procedure and gradient projection methods, we devise a low-complexity suboptimal algorithm for the two subproblems, respectively. Finally, the superiority of our proposed scheme of joint resource allocation and data selection is validated by numerical results.