Theoretical Insights into Line Graph Transformation on Graph Learning

TL;DR

This paper provides theoretical insights into how line graph transformation enhances the ability of graph neural networks and Weisfeiler-Leman tests to distinguish challenging graph structures like CFI and strongly regular graphs.

Contribution

It offers a theoretical analysis of line graph transformation's impact on GNN expressivity, especially for complex graph classes, supported by empirical validation.

Findings

Line graph transformation helps exclude challenging graph properties.

Transformations improve GNN and WL test distinguishability.

Empirical results show increased accuracy and efficiency.

Abstract

Line graph transformation has been widely studied in graph theory, where each node in a line graph corresponds to an edge in the original graph. This has inspired a series of graph neural networks (GNNs) applied to transformed line graphs, which have proven effective in various graph representation learning tasks. However, there is limited theoretical study on how line graph transformation affects the expressivity of GNN models. In this study, we focus on two types of graphs known to be challenging to the Weisfeiler-Leman (WL) tests: Cai-F\"urer-Immerman (CFI) graphs and strongly regular graphs, and show that applying line graph transformation helps exclude these challenging graph properties, thus potentially assist WL tests in distinguishing these graphs. We empirically validate our findings by conducting a series of experiments that compare the accuracy and efficiency of graph isomorphism tests and GNNs on both line-transformed and original graphs across these graph structure types.