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

翻译：本文提出液态-图时间常数（LGTC）网络，一种基于近期液态时间常数（LTC）网络的连续图神经网络（GNN）模型，用于多智能体系统控制。我们利用收缩分析对其稳定性进行解析，并提出一种封闭形式的模型，该模型保留了模型的收缩速率，且无需在每次迭代中求解常微分方程。与图门控神经网络（GGNN）等离散模型相比，所提模型更高的表达能力在保证卓越性能的同时，减少了GNN通常所需的大量通信变量。我们在分布式多智能体控制案例（集群控制）中评估了模型，考虑可变通信范围及非瞬时通信下的可扩展性。