New logic-based graph learning method rivals GNNs in speed and performance

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

Summary written by gemini-2.5-flash-lite from 1 sources. How we write summaries →

IMPACT Offers a faster, GPU-free alternative for graph classification tasks, potentially broadening accessibility.

RANK_REASON The cluster contains an academic paper detailing a new method for graph learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Antti Kuusisto
• graph neural networks
• graph transformers
• Weisfeiler-Leman algorithm

• paper
• other