Diffusion Learning with Partial Agent Participation and Local Updates

TL;DR

This paper introduces an improved diffusion learning method for edge devices that reduces communication overhead and handles device volatility through local updates and partial participation, with proven stability and performance analysis.

Contribution

It proposes a novel diffusion learning algorithm incorporating local updates and partial agent participation, addressing communication and reliability issues in edge networks.

Findings

Algorithm is stable in the mean-square error sense.

Provides a tight analysis of Mean-Square-Deviation performance.

Numerical experiments validate theoretical results.

Abstract

Diffusion learning is a framework that endows edge devices with advanced intelligence. By processing and analyzing data locally and allowing each agent to communicate with its immediate neighbors, diffusion effectively protects the privacy of edge devices, enables real-time response, and reduces reliance on central servers. However, traditional diffusion learning relies on communication at every iteration, leading to communication overhead, especially with large learning models. Furthermore, the inherent volatility of edge devices, stemming from power outages or signal loss, poses challenges to reliable communication between neighboring agents. To mitigate these issues, this paper investigates an enhanced diffusion learning approach incorporating local updates and partial agent participation. Local updates will curtail communication frequency, while partial agent participation will allow for the inclusion of agents based on their availability. We prove that the resulting algorithm is stable in the mean-square error sense and provide a tight analysis of its Mean-Square-Deviation (MSD) performance. Various numerical experiments are conducted to illustrate our theoretical findings.