Homophily principle,\ie {} nodes with the same labels or similar attributes are more likely to
be connected, has been commonly believed to be the main reason for the superiority of …

Graphs are structured data that models complex relations between real-world entities.
Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar …

The ability of Graph Neural Networks (GNNs) to capture long-range and global topology
information is limited by the scope of conventional graph Laplacian, leading to unsatisfactory …

Graph neural networks (GNNs) based on message-passing mechanisms have achieved
advanced results in graph classification tasks. However, their generalization performance …