GQFedWAvg: Optimization-Based Quantized Federated Learning in General Edge Computing Systems

TL;DR

This paper introduces GQFedWAvg, a novel quantized federated learning algorithm optimized for diverse edge computing environments, with convergence analysis and significant performance improvements demonstrated through numerical results.

Contribution

It proposes a new random quantization scheme and a flexible, resource-aware federated learning algorithm with convergence guarantees and optimized parameters.

Findings

GQFedWAvg outperforms existing FL algorithms in numerical tests.

The algorithm effectively adapts to varying computing and communication resources.

Convergence error is minimized under time and energy constraints.

Abstract

The optimal implementation of federated learning (FL) in practical edge computing systems has been an outstanding problem. In this paper, we propose an optimization-based quantized FL algorithm, which can appropriately fit a general edge computing system with uniform or nonuniform computing and communication resources at the workers. Specifically, we first present a new random quantization scheme and analyze its properties. Then, we propose a general quantized FL algorithm, namely GQFedWAvg. Specifically, GQFedWAvg applies the proposed quantization scheme to quantize wisely chosen model update-related vectors and adopts a generalized mini-batch stochastic gradient descent (SGD) method with the weighted average local model updates in global model aggregation. Besides, GQFedWAvg has several adjustable algorithm parameters to flexibly adapt to the computing and communication resources at the server and workers. We also analyze the convergence of GQFedWAvg. Next, we optimize the algorithm parameters of GQFedWAvg to minimize the convergence error under the time and energy constraints. We successfully tackle the challenging non-convex problem using general inner approximation (GIA) and multiple delicate tricks. Finally, we interpret GQFedWAvg's function principle and show its considerable gains over existing FL algorithms using numerical results.