collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2025

FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervision

Xiangyu Dong, Xingyi Zhang, Sibo Wang

Graph-level anomaly detection (GAD) is critical in diverse domains such as drug discovery, yet high labeling costs and dataset imbalance hamper the performance of Graph Neural Netw…

cs.LG2025

Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection

Xiping Li, Xiangyu Dong, Xingyi Zhang +7

Graph Anomaly Detection (GAD) in heterogeneous networks presents unique challenges due to node and edge heterogeneity. Existing Graph Neural Network (GNN) methods primarily focus o…

cs.LG2025

SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labels

Xiangyu Dong, Xingyi Zhang, Lei Chen +2

Node Anomaly Detection (NAD) has gained significant attention in the deep learning community due to its diverse applications in real-world scenarios. Existing NAD methods primarily…

cs.LG2024

SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection

Xiangyu Dong, Xingyi Zhang, Yanni Sun +3

The smoothing issue in graph learning leads to indistinguishable node representations, posing significant challenges for graph-related tasks. However, our experiments reveal that t…

cs.LG2024

Towards Deeper Understanding of PPR-based Embedding Approaches: A Topological Perspective

Xingyi Zhang, Zixuan Weng, Sibo Wang

Node embedding learns low-dimensional vectors for nodes in the graph. Recent state-of-the-art embedding approaches take Personalized PageRank (PPR) as the proximity measure and fac…

cs.LG2024

Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection

Xiangyu Dong, Xingyi Zhang, Sibo Wang

Graph-level anomaly detection has gained significant attention as it finds applications in various domains, such as cancer diagnosis and enzyme prediction. However, existing method…