Deep Learning-Based Average Consensus

TL;DR

This paper introduces a deep learning method to optimize time-varying weights in linear average consensus algorithms, significantly improving convergence speed and accuracy in complex networks.

Contribution

It presents a novel data-driven approach that uses neural networks to tune weights for faster consensus in complex networks, extending to infinite-time scenarios.

Findings

Achieved smaller consensus errors than baseline methods

Demonstrated effectiveness in complex network scenarios

Extended approach to infinite-time window problems

Abstract

In this study, we analyzed the problem of accelerating the linear average consensus algorithm for complex networks. We propose a data-driven approach to tuning the weights of temporal (i.e., time-varying) networks using deep learning techniques. Given a finite-time window, the proposed approach first unfolds the linear average consensus protocol to obtain a feedforward signal-flow graph, which is regarded as a neural network. The edge weights of the obtained neural network are then trained using standard deep learning techniques to minimize consensus error over a given finite-time window. Through this training process, we obtain a set of optimized time-varying weights, which yield faster consensus for a complex network. We also demonstrate that the proposed approach can be extended for infinite-time window problems. Numerical experiments revealed that our approach can achieve a significantly smaller consensus error compared to baseline strategies.