Graph anomaly detection aims to identify the atypical substructures and has attracted an
increasing amount of research attention due to its profound impacts in a variety of …

Abstract Graph Contrastive Learning (GCL) a Self-Supervised Learning (SSL) architecture
tailored for graphs has shown notable potential for mitigating label scarcity. Its core idea is to …

For real-world graph data, the node class distribution is inherently imbalanced and long-
tailed, which naturally leads to a few-shot learning scenario with limited nodes labeled for …

Graph neural networks have shown impressive capabilities in solving various graph
learning tasks, particularly excelling in node classification. However, their effectiveness can …

Breast cancer has become the most common cancer in the world. Early diagnosis and
treatment can greatly improve the survival rate of breast cancer patients. Computer …

Mixup is an efficient data augmentation technique, which improves generalization by
interpolating random examples. While numerous approaches have been developed for …

For real-world graph data, the node class distribution is inherently imbalanced and long-
tailed, which naturally leads to a few-shot learning scenario with limited nodes labeled for …

Graph structures have attracted much research attention for carrying complex relational
information. Based on graphs, many algorithms and tools are proposed and developed for …

In recent years, graph representation learning has achieved remarkable success while
suffering from low-quality data problems. As a mature technology to improve data quality in …

Graph anomaly detection (GAD) has wide applications in real-world networked systems. In
many scenarios, people need to identify anomalies on new (sub) graphs, but they may lack …