Convergence Acceleration in Wireless Federated Learning: A Stackelberg Game Approach

TL;DR

This paper introduces a Stackelberg game framework to optimize device selection and resource allocation in wireless federated learning, significantly accelerating convergence and improving training efficiency under energy constraints.

Contribution

It proposes a novel Stackelberg game approach for joint optimization of convergence speed and latency in wireless federated learning, including an AoU-based device selection algorithm.

Findings

The AoU-based device selection improves convergence rate.

The proposed method efficiently utilizes sub-channels.

Simulation shows faster convergence and resource efficiency.

Abstract

This paper studies issues that arise with respect to the joint optimization for convergence time in federated learning over wireless networks (FLOWN). We consider the criterion and protocol for selection of participating devices in FLOWN under the energy constraint and derive its impact on device selection. In order to improve the training efficiency, age-of-information (AoI) enables FLOWN to assess the freshness of gradient updates among participants. Aiming to speed up convergence, we jointly investigate global loss minimization and latency minimization in a Stackelberg game based framework. Specifically, we formulate global loss minimization as a leader-level problem for reducing the number of required rounds, and latency minimization as a follower-level problem to reduce time consumption of each round. By decoupling the follower-level problem into two sub-problems, including resource allocation and sub-channel assignment, we achieve an optimal strategy of the follower through monotonic optimization and matching theory. At the leader-level, we derive an upper bound of convergence rate and subsequently reformulate the global loss minimization problem and propose a new age-of-update (AoU) based device selection algorithm. Simulation results indicate the superior performance of the proposed AoU based device selection scheme in terms of the convergence rate, as well as efficient utilization of available sub-channels.