Enhancing GNNs with Architecture-Agnostic Graph Transformations: A Systematic Analysis
This work addresses the lack of best practices in GNN pre-processing for researchers, though it is incremental as it builds on existing transformation techniques.
The study systematically analyzed how graph transformations as pre-processing steps affect the expressivity of GNNs across standard datasets, finding that augmenting node features with centrality measures consistently improves expressivity but introduces trade-offs like numerical inaccuracies and limitations on complex tasks.
In recent years, a wide variety of graph neural network (GNN) architectures have emerged, each with its own strengths, weaknesses, and complexities. Various techniques, including rewiring, lifting, and node annotation with centrality values, have been employed as pre-processing steps to enhance GNN performance. However, there are no universally accepted best practices, and the impact of architecture and pre-processing on performance often remains opaque. This study systematically explores the impact of various graph transformations as pre-processing steps on the performance of common GNN architectures across standard datasets. The models are evaluated based on their ability to distinguish non-isomorphic graphs, referred to as expressivity. Our findings reveal that certain transformations, particularly those augmenting node features with centrality measures, consistently improve expressivity. However, these gains come with trade-offs, as methods like graph encoding, while enhancing expressivity, introduce numerical inaccuracies widely-used python packages. Additionally, we observe that these pre-processing techniques are limited when addressing complex tasks involving 3-WL and 4-WL indistinguishable graphs.