Event-Triggered Gossip for Distributed Learning

TL;DR

This paper introduces an event-triggered gossip framework for distributed learning that significantly reduces communication overhead by enabling nodes to autonomously decide when to exchange information, maintaining performance while cutting transmissions by over 70%.

Contribution

It proposes a novel adaptive communication control mechanism for decentralized decision-making in distributed learning, with theoretical convergence analysis and practical simulation validation.

Findings

Achieves 71.61% reduction in communication transmissions.

Maintains comparable learning performance with reduced communication.

Provides convergence guarantees under non-convex objectives.

Abstract

While distributed learning offers a new learning paradigm for distributed network with no central coordination, it is constrained by communication bottleneck between nodes. We develop a new event-triggered gossip framework for distributed learning to reduce inter-node communication overhead. The framework introduces an adaptive communication control mechanism that enables each node to autonomously decide in a fully decentralized fashion when to exchange model information with its neighbors based on local model deviations. We analyze the ergodic convergence of the proposed framework under noconvex objectives and interpret the convergence guarantees under different triggering conditions. Simulation results show that the proposed framework achieves substantially lower communication overhead than the state-of-the-art distributed learning methods, reducing cumulative point-to-point transmissions by \textbf{71.61\%} with only a marginal performance loss, compared with the conventional full-communication baseline.