Data-centric AI, with its primary focus on the collection, management, and utilization of data
to drive AI models and applications, has attracted increasing attention in recent years. In this …

Graph representation learning has shown effectiveness when testing and training graph
data come from the same distribution, but most existing approaches fail to generalize under …

The issue of distribution shifts is emerging as a critical concern in graph representation
learning. From the perspective of invariant learning and stable learning, a recently well …

Abstract Out-of-distribution (OOD) learning deals with scenarios in which training and test
data follow different distributions. Although general OOD problems have been intensively …

There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so
that research on out-of-distribution (OOD) generalization comes into the spotlight …

Dynamic graph neural networks (DyGNNs) have demonstrated powerful predictive abilities
by exploiting graph structural and temporal dynamics. However, the existing DyGNNs fail to …

Abstract Recent studies on Graph Neural Networks (GNNs) provide both empirical and
theoretical evidence supporting their effectiveness in capturing structural patterns on both …

Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …

In the past few years, graph neural networks (GNNs) have become the de facto model of
choice for graph classification. While, from the theoretical viewpoint, most GNNs can operate …

Graph anomaly detection (GAD) is a challenging binary classification problem due to its
different structural distribution between anomalies and normal nodes---abnormal nodes are …