Graph neural networks, a powerful deep learning tool to model graph-structured data, have
demonstrated remarkable performance on numerous graph learning tasks. To address the …

Most existing deep learning models are trained based on the closed-world assumption,
where the test data is assumed to be drawn iid from the same distribution as the training …

Graph Neural Networks (GNNs) have exhibited impressive performance in many graph
learning tasks. Nevertheless, the performance of GNNs can deteriorate when the input …

Social Event Detection (SED) aims to identify significant events from social streams, and has
a wide application ranging from public opinion analysis to risk management. In recent years …

A fundamental challenge of bipartite graph representation learning is how to extract
informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to …

Graph contrastive learning (GCL) has been widely applied to text classification tasks due to
its ability to generate self-supervised signals from unlabeled data, thus facilitating model …

Self-supervised representation learning on text-attributed graphs, which aims to create
expressive and generalizable representations for various downstream tasks, has received …

Graph‐structured data, ranging from social networks to financial transaction networks, from
citation networks to gene regulatory networks, have been widely used for modeling a myriad …

Graph Neural Networks (GNNs) have emerged as a prominent framework for graph mining,
leading to significant advances across various domains. Stemmed from the node-wise …

Graph neural networks (GNNs) based on message passing have achieved remarkable
performance in graph machine learning. By combining it with the power of pseudo labeling …