Limit Analysis of Graph Neural Networks with Wireless Conflict Graphs
2026-06-02 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how Graph Neural Networks (GNNs), which are models that work with data structured as graphs, can be used to allocate wireless network resources efficiently. They focused on sparse wireless networks, where each device connects to only a few others, modeled using Random Geometric Graphs (RGGs). By comparing these graphs to more regular grid-like graphs, the authors provided theoretical guarantees about how well GNNs trained on small networks perform when applied to larger ones. They tested their ideas on the link scheduling problem and showed their approach works better than existing methods at scale. Lastly, they looked at how their assumptions affect real-world results.
Graph Neural NetworksWireless resource allocationRandom Geometric GraphsSparse networksTransferabilityConflict graphsLink schedulingDeterministic Grid GraphsInterference modeling
Authors
Romina Garcia Camargo, Zhiyang Wang, Alejandro Ribeiro
Abstract
Graph Neural Networks (GNNs) have emerged as a powerful tool for wireless resource allocation that leverages the underlying graph structure of communication networks. Their transferability property enables models trained on small-scale graphs to generalize to large-scale deployments with little performance deterioration, a desirable property for currently growing networks. Wireless networks are sparse regimes, where a single node is connected to a small number of other users. This work establishes theoretical results for transferability of GNNs over graphs derived from sparse Random Geometric Graphs (RGGs). In particular, we focus on conflict graphs of RGGs used to model interference among links. Our approach considers the closeness between RGGs and Deterministic Grid Graphs (DGG) to establish bounds in the performance loss when a model is transferred across scales. We validate our theoretical findings through the problem of link scheduling, demonstrating that our learned policies consistently outperform existing benchmarks at scale. Finally, we examine the impact of our theoretical assumptions on empirical performance.