Distributed Scheduling using Graph Neural Networks

TL;DR

This paper introduces a graph neural network-based distributed scheduler for wireless networks that significantly improves upon traditional greedy methods by incorporating topological information, reducing suboptimality.

Contribution

It proposes a novel GCN-based MWIS solver that learns topology-aware embeddings to enhance distributed scheduling in wireless networks.

Findings

Reduces suboptimality gap by half in small to medium networks.

Leverages topological information to improve scheduling accuracy.

Maintains minimal complexity increase with good generalizability.

Abstract

A fundamental problem in the design of wireless networks is to efficiently schedule transmission in a distributed manner. The main challenge stems from the fact that optimal link scheduling involves solving a maximum weighted independent set (MWIS) problem, which is NP-hard. For practical link scheduling schemes, distributed greedy approaches are commonly used to approximate the solution of the MWIS problem. However, these greedy schemes mostly ignore important topological information of the wireless networks. To overcome this limitation, we propose a distributed MWIS solver based on graph convolutional networks (GCNs). In a nutshell, a trainable GCN module learns topology-aware node embeddings that are combined with the network weights before calling a greedy solver. In small- to middle-sized wireless networks with tens of links, even a shallow GCN-based MWIS scheduler can leverage the topological information of the graph to reduce in half the suboptimality gap of the distributed greedy solver with good generalizability across graphs and minimal increase in complexity.