Graph clustering has received significant attention in recent years due to the breakthrough of
graph neural networks (GNNs). However, GNNs frequently assume strong data homophily …

With the rapid development of the World Wide Web (WWW), heterogeneous graphs (HG)
have explosive growth. Recently, heterogeneous graph neural network (HGNN) has shown …

Graph structure learning is a well-established problem that aims at optimizing graph
structures adaptive to specific graph datasets to help message passing neural networks (ie …

Graph contrastive learning (GCL) is the most representative and prevalent self-supervised
learning approach for graph-structured data. Despite its remarkable success, existing GCL …

We bridge two research directions on graph neural networks (GNNs), by formalizing the
relation between heterophily of node labels (ie, connected nodes tend to have dissimilar …

Spectral-temporal graph neural network is a promising abstraction underlying most time
series forecasting models that are based on graph neural networks (GNNs). However, more …

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 …

Accurately predicting the binding affinity between proteins and ligands is crucial for drug
discovery. Recent advances in graph neural networks (GNNs) have made significant …

Spectral Graph Neural Networks (GNNs) are gaining attention because they can surpass the
limitations of message-passing GNNs by learning spectral filters that capture essential …

In the realm of cross-network tasks, graph domain adaptation is an effective tool due to its
ability to transfer abundant labels from nodes in the source domain to those in the target …