Chordless Structure: A Pathway to Simple and Expressive GNNs
This addresses the need for more expressive and efficient GNNs in graph learning tasks, though it appears incremental by building on prior structured information methods.
The paper tackles the problem of enhancing Graph Neural Networks (GNNs) expressiveness by proposing a chordless structure-based approach, which achieves better performance than existing GNNs with lower computational costs, as demonstrated on real-world datasets.
Researchers have proposed various methods of incorporating more structured information into the design of Graph Neural Networks (GNNs) to enhance their expressiveness. However, these methods are either computationally expensive or lacking in provable expressiveness. In this paper, we observe that the chords increase the complexity of the graph structure while contributing little useful information in many cases. In contrast, chordless structures are more efficient and effective for representing the graph. Therefore, when leveraging the information of cycles, we choose to omit the chords. Accordingly, we propose a Chordless Structure-based Graph Neural Network (CSGNN) and prove that its expressiveness is strictly more powerful than the k-hop GNN (KPGNN) with polynomial complexity. Experimental results on real-world datasets demonstrate that CSGNN outperforms existing GNNs across various graph tasks while incurring lower computational costs and achieving better performance than the GNNs of 3-WL expressiveness.