Exploring the impact of adaptive rewiring in Graph Neural Networks

TL;DR

This paper investigates adaptive sparsification and rewiring techniques in Graph Neural Networks to improve efficiency and scalability, demonstrating their effectiveness in electrical grid reliability assessment.

Contribution

It introduces an adaptive rewiring method for GNNs that dynamically adjusts connectivity during training, enhancing performance and scalability in large-scale applications.

Findings

Adaptive rewiring improves GNN performance.

Excessive sparsity can hinder complex pattern learning.

Combining sparsification with early stopping yields promising results.

Abstract

This paper explores sparsification methods as a form of regularization in Graph Neural Networks (GNNs) to address high memory usage and computational costs in large-scale graph applications. Using techniques from Network Science and Machine Learning, including Erd\H{o}s-R\'enyi for model sparsification, we enhance the efficiency of GNNs for real-world applications. We demonstrate our approach on N-1 contingency assessment in electrical grids, a critical task for ensuring grid reliability. We apply our methods to three datasets of varying sizes, exploring Graph Convolutional Networks (GCN) and Graph Isomorphism Networks (GIN) with different degrees of sparsification and rewiring. Comparison across sparsification levels shows the potential of combining insights from both research fields to improve GNN performance and scalability. Our experiments highlight the importance of tuning sparsity parameters: while sparsity can improve generalization, excessive sparsity may hinder learning of complex patterns. Our adaptive rewiring approach, particularly when combined with early stopping, proves promising by allowing the model to adapt its connectivity structure during training. This research contributes to understanding how sparsity can be effectively leveraged in GNNs for critical applications like power grid reliability analysis.