Deep Graph Anomaly Detection: A Survey and New Perspectives
Graph anomaly detection (GAD), which aims to identify unusual graph instances (nodes,
edges, subgraphs, or graphs), has attracted increasing attention in recent years due to its …
edges, subgraphs, or graphs), has attracted increasing attention in recent years due to its …
Prototype-oriented hypergraph representation learning for anomaly detection in tabular data
S Li, Y Lu, S Jiu, H Huang, G Yang, J Yu - Information Processing & …, 2025 - Elsevier
Anomaly detection in tabular data holds significant importance across various industries
such as manufacturing, healthcare, and finance. However, existing methods are constrained …
such as manufacturing, healthcare, and finance. However, existing methods are constrained …
Graph Anomaly Detection via Multi-View Discriminative Awareness Learning
J Lian, X Wang, X Lin, Z Wu, S Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
With the deeper research on attributed networks, graph anomaly detection is becoming an
increasingly important topic. It aims to identify patterns deviating from a majority of nodes …
increasingly important topic. It aims to identify patterns deviating from a majority of nodes …
Simultaneously Detecting Node and Edge Level Anomalies on Heterogeneous Attributed Graphs
R Fathony, J Ng, J Chen - 2024 International Joint Conference …, 2024 - ieeexplore.ieee.org
In complex systems like social media and financial transactions, diverse entities (users,
groups, products) interact through a multitude of relationships (friendships, comments …
groups, products) interact through a multitude of relationships (friendships, comments …
SmoothGNN: Smoothing-based GNN for Unsupervised Node Anomaly Detection
The smoothing issue leads to indistinguishable node representations, which poses a
significant challenge in the field of graph learning. However, this issue also presents an …
significant challenge in the field of graph learning. However, this issue also presents an …
Magnitude-Contrastive Network for Unsupervised Graph Anomaly Detection
Effectively identifying anomalous nodes within networks is crucial for various applications,
such as fraud detection, network intrusion prevention, and social network activity monitoring …
such as fraud detection, network intrusion prevention, and social network activity monitoring …