Anomalies are rare observations (eg, data records or events) that deviate significantly from
the others in the sample. Over the past few decades, research on anomaly mining has …

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 …

Federated Learning (FL) is a machine learning paradigm that allows decentralized clients to
learn collaboratively without sharing their private data. However, excessive computation and …

Deep learning on graphs has attracted significant interests recently. However, most of the
works have focused on (semi-) supervised learning, resulting in shortcomings including …

In recent years, graph neural networks (GNNs) have emerged as a successful tool in a
variety of graph-related applications. However, the performance of GNNs can be …

Graph contrastive learning (GCL) alleviates the heavy reliance on label information for
graph representation learning (GRL) via self-supervised learning schemes. The core idea is …

Detecting which nodes in graphs are outliers is a relatively new machine learning task with
numerous applications. Despite the proliferation of algorithms developed in recent years for …

Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable
dissimilarity compared to the majority in a collection. However, current works primarily focus …

Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-
scale condensed graph as its substitution, has immediate benefits for various graph learning …

Unsupervised graph representation learning (UGRL) has drawn increasing research
attention and achieved promising results in several graph analytic tasks. Relying on the …