Fully Distributed Online Training of Graph Neural Networks in Networked Systems

Rostyslav Olshevskyi, Zhongyuan Zhao, Kevin S Chan, Gunjan Verma, Ananthram Swami, Santiago Segarra

Abstract: Graph neural networks (GNNs) are powerful tools for developing scalable, decentralized artificial intelligence in large-scale networked systems, such as wireless networks, power grids, and transportation networks. Currently, GNNs in networked systems mostly follow a paradigm of `centralized training, distributed execution', which limits their adaptability and slows down their development cycles. In this work, we fill this gap for the first time by developing a communication-efficient, fully distributed online training approach for GNNs applied to large networked systems. For a mini-batch with B samples, our approach of training an L-layer GNN only adds L rounds of message passing to the LB rounds required by GNN inference, with doubled message sizes. Through numerical experiments in graph-based node regression, power allocation, and link scheduling in wireless networks, we demonstrate the effectiveness of our approach in training GNNs under supervised, unsupervised, and reinforcement learning paradigms.