Limit Analysis of Graph Neural Networks with Wireless Conflict Graphs
Provides theoretical guarantees for GNN transferability in wireless networks, a practical problem for network operators deploying scalable resource allocation solutions.
This paper establishes theoretical bounds on the transferability of GNNs for wireless resource allocation on sparse random geometric graphs, showing that policies trained on small graphs generalize to large-scale deployments with minimal performance loss, and empirically outperform benchmarks in link scheduling.
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.