Local Vertex Colouring Graph Neural Networks

1 code implementation • 10 Mar 2024 • Shouheng Li, Dongwoo Kim, Qing Wang

Specifically, we propose a new vertex colouring scheme and demonstrate that classical search algorithms can efficiently compute graph representations that extend beyond the 1-WL.

Generalization of Graph Neural Networks through the Lens of Homomorphism

no code implementations • 10 Mar 2024 • Shouheng Li, Dongwoo Kim, Qing Wang

In this work, we propose to study the generalization of GNNs through a novel perspective - analyzing the entropy of graph homomorphism.

Generalization Bounds

N-WL: A New Hierarchy of Expressivity for Graph Neural Networks

no code implementations • The Eleventh International Conference on Learning Representations 2023 • Qing Wang, Dillon Chen, Asiri Wijesinghe, Shouheng Li, Muhammad Farhan

The expressive power of Graph Neural Networks (GNNs) is fundamental for understanding their capabilities and limitations, i. e., what graph properties can or cannot be learnt by a GNN.

Restructuring Graph for Higher Homophily via Adaptive Spectral Clustering

no code implementations • 6 Jun 2022 • Shouheng Li, Dongwoo Kim, Qing Wang

While a growing body of literature has been studying new Graph Neural Networks (GNNs) that work on both homophilic and heterophilic graphs, little has been done on adapting classical GNNs to less-homophilic graphs.

Clustering Node Classification

Global Node Attentions via Adaptive Spectral Filters

no code implementations • 1 Jan 2021 • Shouheng Li, Dongwoo Kim, Qing Wang

The proposed model has been shown to generalize well to both assortative and disassortative graphs.

Node Classification