Liquid-Graph Time-Constant Network for Multi-Agent Systems Control
Abstract
In this paper, we propose the Liquid-Graph Time-constant (LGTC) network, a continuous graph neural network(GNN) model for control of multi-agent systems based on therecent Liquid Time Constant (LTC) network. We analyse itsstability leveraging contraction analysis and propose a closed-form model that preserves the model contraction rate and doesnot require solving an ODE at each iteration. Compared todiscrete models like Graph Gated Neural Networks (GGNNs),the higher expressivity of the proposed model guaranteesremarkable performance while reducing the large amountof communicated variables normally required by GNNs. Weevaluate our model on a distributed multi-agent control casestudy (flocking) taking into account variable communicationrange and scalability under non-instantaneous communication
Keywords
Cite
@article{arxiv.2404.13982,
title = {Liquid-Graph Time-Constant Network for Multi-Agent Systems Control},
author = {Antonio Marino and Claudio Pacchierotti and Paolo Robuffo Giordano},
journal= {arXiv preprint arXiv:2404.13982},
year = {2025}
}
Comments
arXiv admin note: text overlap with arXiv:2305.19235