Recent years have witnessed fast developments of graph neural networks (GNNs) that have
benefited myriads of graph analytic tasks and applications. In general, most GNNs depend …

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 …

This work studies the evaluation of explaining graph neural networks (GNNs), which is
crucial to the credibility of post-hoc explainability in practical usage. Conventional evaluation …

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 …

With a long history of traditional Graph Anomaly Detection (GAD) algorithms and recently
popular Graph Neural Networks (GNNs), it is still not clear (1) how they perform under a …

Graph anomaly detection (GAD) suffers from heterophily—abnormal nodes are sparse so
that they are connected to vast normal nodes. The current solutions upon Graph Neural …

Graph representation learning on vast datasets, like web data, has made significant strides.
However, the associated computational and storage overheads raise concerns. In sight of …

Anomaly detection (AD) is a crucial task in machine learning with various applications, such
as detecting emerging diseases, identifying financial frauds, and detecting fake news …

Anomalous node detection in a static graph faces significant challenges due to the rarity of
anomalies and the substantial cost of labeling their deviant structure and attribute patterns …

We reveal a one-class homophily phenomenon, which is one prevalent property we find
empirically in real-world graph anomaly detection (GAD) datasets, ie, normal nodes tend to …