195 citations · 213 across the 14 of their papers we have counts for
6 papers · 1 filter
Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
Fanzhen Liu, Xiaoxiao Ma, Jian Yang +6
Enhancing the interpretability of graph neural networks (GNNs) is crucial to ensure their safe and fair deployment. Recent work has introduced self-explainable GNNs that generate e…
Discriminative Graph-level Anomaly Detection via Dual-students-teacher Model
Fu Lin, Xuexiong Luo, Jia Wu +4
Different from the current node-level anomaly detection task, the goal of graph-level anomaly detection is to find abnormal graphs that significantly differ from others in a graph…
State of the Art and Potentialities of Graph-level Learning
Zhenyu Yang, Ge Zhang, Jia Wu +9
Graphs have a superior ability to represent relational data, like chemical compounds, proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as inp…
DAGAD: Data Augmentation for Graph Anomaly Detection
Fanzhen Liu, Xiaoxiao Ma, Jia Wu +7
Graph anomaly detection in this paper aims to distinguish abnormal nodes that behave differently from the benign ones accounting for the majority of graph-structured instances. Rec…
Graph-level Neural Networks: Current Progress and Future Directions
Ge Zhang, Jia Wu, Jian Yang +6
Graph-structured data consisting of objects (i.e., nodes) and relationships among objects (i.e., edges) are ubiquitous. Graph-level learning is a matter of studying a collection of…
A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
Xiaoxiao Ma, Jia Wu, Shan Xue +5
Anomalies represent rare observations (e.g., data records or events) that deviate significantly from others. Over several decades, research on anomaly mining has received increasin…