Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization
Researchers have developed new variants of the Weisfeiler-Leman algorithm for graph classification, which involve modifying the underlying logical framework. These variants allow graph data to be tabularized, enabling the application of standard tabular data methods. Experiments on 14 datasets showed that this approach achieves predictive performance comparable to graph neural networks and graph transformers, while being significantly faster and not requiring GPU resources. AI
IMPACT Offers a faster, GPU-free alternative for graph classification tasks, potentially broadening accessibility.