# Graph Anomaly Detection with Unsupervised GNNs

arXiv: https://arxiv.org/abs/2210.09535 · HTML: https://mlsanity.com/paper/2210.09535/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 58 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 24 of 24)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Learning Convolutional Neural Networks for Graphs](https://mlsanity.com/paper/1605.05273/) (2016)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [A Comprehensive Survey on Graph Anomaly Detection with Deep Learning](https://mlsanity.com/paper/2106.07178/) (2021)
- [Graph-based Anomaly Detection and Description: A Survey](https://mlsanity.com/paper/1404.4679/) (2014)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Fake News Detection on Social Media using Geometric Deep Learning](https://mlsanity.com/paper/1902.06673/) (2019)
- [Graph Embedded Pose Clustering for Anomaly Detection](https://mlsanity.com/paper/1912.11850/) (2019)
- [Propagation Kernels](https://mlsanity.com/paper/1410.3314/) (2014)
- [On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insights](https://mlsanity.com/paper/2012.12931/) (2020)
- [Unsupervised Model Selection for Variational Disentangled Representation Learning](https://mlsanity.com/paper/1905.12614/) (2019)
- [Graph Kernels: A Survey](https://mlsanity.com/paper/1904.12218/) (2019)
- [Fast Memory-efficient Anomaly Detection in Streaming Heterogeneous Graphs](https://mlsanity.com/paper/1602.04844/) (2016)
- [Scalable Anomaly Ranking of Attributed Neighborhoods](https://mlsanity.com/paper/1601.06711/) (2016)
- [How to Evaluate the Quality of Unsupervised Anomaly Detection Algorithms?](https://mlsanity.com/paper/1607.01152/) (2016)
- [Semi-supervised Anomaly Detection on Attributed Graphs](https://mlsanity.com/paper/2002.12011/) (2020)
- [EdgeCentric: Anomaly Detection in Edge-Attributed Networks](https://mlsanity.com/paper/1510.05544/) (2015)
- [One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks](https://mlsanity.com/paper/2002.09594/) (2020)

## Built on by (most cited first, 8 of 8)

- [Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy](https://mlsanity.com/paper/2410.20366/) (2024)
- [Graph Neural Networks based Log Anomaly Detection and Explanation](https://mlsanity.com/paper/2307.00527/) (2023)
- [On the Detection of Reviewer-Author Collusion Rings From Paper Bidding](https://mlsanity.com/paper/2402.07860/) (2024)
- [Evolve Path Tracer: Early Detection of Malicious Addresses in Cryptocurrency](https://mlsanity.com/paper/2301.05412/) (2023)
- [ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approach](https://mlsanity.com/paper/2311.07355/) (2023)
- [Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.13251/) (2024)
- [Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection](https://mlsanity.com/paper/2404.16366/) (2024)
- [A Survey on Graph Neural Networks for Fraud Detection in Ride Hailing Platforms](https://mlsanity.com/paper/2512.23777/) (2025)

## Abstract (arXiv)

Graph-based anomaly detection finds numerous applications in the real-world. Thus, there exists extensive literature on the topic that has recently shifted toward deep detection models due to advances in deep learning and graph neural networks (GNNs). A vast majority of prior work focuses on detecting node/edge/subgraph anomalies within a single graph, with much less work on graph-level anomaly detection in a graph database. This work aims to fill two gaps in the literature: We (1) design GLAM, an end-to-end graph-level anomaly detection model based on GNNs, and (2) focus on unsupervised model selection, which is notoriously hard due to lack of any labels, yet especially critical for deep NN based models with a long list of hyper-parameters. Further, we propose a new pooling strategy for graph-level embedding, called MMD-pooling, that is geared toward detecting distribution anomalies which has not been considered before. Through extensive experiments on 15 real-world datasets, we show that (i) GLAM outperforms node-level and two-stage (i.e. not end-to-end) baselines, and (ii) model selection picks a significantly more effective model than expectation (i.e. average) -- without using any labels -- among candidates with otherwise large variation in performance.