Graph anomaly detection with graph neural networks: Current status and challenges

H Kim, BS Lee, WY Shin, S Lim - IEEE Access, 2022‏ - ieeexplore.ieee.org
Graphs are used widely to model complex systems, and detecting anomalies in a graph is
an important task in the analysis of complex systems. Graph anomalies are patterns in a …

Deep isolation forest for anomaly detection

H Xu, G Pang, Y Wang, Y Wang - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Isolation forest (iForest) has been emerging as arguably the most popular anomaly detector
in recent years due to its general effectiveness across different benchmarks and strong …

Towards self-interpretable graph-level anomaly detection

Y Liu, K Ding, Q Lu, F Li… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
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 …

Deep graph anomaly detection: A survey and new perspectives

H Qiao, H Tong, B An, I King, C Aggarwal… - arxiv preprint arxiv …, 2024‏ - arxiv.org
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 …

Good-d: On unsupervised graph out-of-distribution detection

Y Liu, K Ding, H Liu, S Pan - … international conference on web search and …, 2023‏ - dl.acm.org
Most existing deep learning models are trained based on the closed-world assumption,
where the test data is assumed to be drawn iid from the same distribution as the training …

Arc: a generalist graph anomaly detector with in-context learning

Y Liu, S Li, Y Zheng, Q Chen… - Advances in Neural …, 2025‏ - proceedings.neurips.cc
Graph anomaly detection (GAD), which aims to identify abnormal nodes that differ from the
majority within a graph, has garnered significant attention. However, current GAD methods …

Graphde: A generative framework for debiased learning and out-of-distribution detection on graphs

Z Li, Q Wu, F Nie, J Yan - Advances in Neural Information …, 2022‏ - proceedings.neurips.cc
Despite the remarkable success of graph neural networks (GNNs) for graph representation
learning, they are generally built on the (unreliable) iid assumption across training and …

Dual-discriminative graph neural network for imbalanced graph-level anomaly detection

G Zhang, Z Yang, J Wu, J Yang, S Xue… - Advances in …, 2022‏ - proceedings.neurips.cc
Graph-level anomaly detection aims to distinguish anomalous graphs in a graph dataset
from normal graphs. Anomalous graphs represent a very few but essential patterns in the …

Deep graph level anomaly detection with contrastive learning

X Luo, J Wu, J Yang, S Xue, H Peng, C Zhou… - Scientific Reports, 2022‏ - nature.com
Graph level anomaly detection (GLAD) aims to spot anomalous graphs that structure pattern
and feature information are different from most normal graphs in a graph set, which is rarely …

A data-centric framework to endow graph neural networks with out-of-distribution detection ability

Y Guo, C Yang, Y Chen, J Liu, C Shi, J Du - Proceedings of the 29th …, 2023‏ - dl.acm.org
Out-of-distribution (OOD) detection, which aims to identify OOD samples from in-distribution
(ID) ones in test time, has become an essential problem in machine learning. However …