4 papers
Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors
Junru Zhou, Cai Zhou, Xiyuan Wang +2
A popular way to improve the expressive power of graph neural networks (GNNs) is to use Laplacian eigenvectors as additional node features, since they can serve both as structural…
Masked Language Models are Good Heterogeneous Graph Generalizers
Jinyu Yang, Cheng Yang, Shanyuan Cui +5
Heterogeneous graph neural networks (HGNNs) excel at capturing structural and semantic information in heterogeneous graphs (HGs), while struggling to generalize across domains and…
GNNs as Predictors of Agentic Workflow Performances
Yuanshuo Zhang, Yuchen Hou, Bohan Tang +4
Agentic workflows invoked by Large Language Models (LLMs) have achieved remarkable success in handling complex tasks. However, optimizing such workflows is costly and inefficient i…
Fine-Grained Expressive Power of Weisfeiler-Leman: A Homomorphism Counting Perspective
Junru Zhou, Muhan Zhang
The ability of graph neural networks (GNNs) to count homomorphisms has recently been proposed as a practical and fine-grained measure of their expressive power. Although several ex…