# Discriminative Graph-level Anomaly Detection via Dual-students-teacher Model

arXiv: https://arxiv.org/abs/2308.01947 · HTML: https://mlsanity.com/paper/2308.01947/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 30 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 14 of 14)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Fake News Detection on Social Media: A Data Mining Perspective](https://mlsanity.com/paper/1708.01967/) (2017)
- [A Comprehensive Survey on Graph Anomaly Detection with Deep Learning](https://mlsanity.com/paper/2106.07178/) (2021)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks](https://mlsanity.com/paper/2002.03665/) (2020)
- [Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection](https://mlsanity.com/paper/2108.09896/) (2021)
- [Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation](https://mlsanity.com/paper/2112.10063/) (2021)
- [GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection](https://mlsanity.com/paper/2211.04208/) (2022)
- [SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks](https://mlsanity.com/paper/1908.03849/) (2019)
- [Graph Contrastive Learning for Anomaly Detection](https://mlsanity.com/paper/2108.07516/) (2021)
- [DAGAD: Data Augmentation for Graph Anomaly Detection](https://mlsanity.com/paper/2210.09766/) (2022)
- [DenseAlert: Incremental Dense-Subtensor Detection in Tensor Streams](https://mlsanity.com/paper/1706.03374/) (2017)
- [Spade: A Real-Time Fraud Detection Framework on Evolving Graphs (Complete Version)](https://mlsanity.com/paper/2211.06977/) (2022)

## Built on by (most cited first, 6 of 6)

- [Deep Graph Anomaly Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2409.09957/) (2024)
- [Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.13251/) (2024)
- [FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.00383/) (2024)
- [Generalist Graph Anomaly Detection via Prototype-Based Distillation](https://mlsanity.com/paper/2605.26857/) (2026)
- [Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning](https://mlsanity.com/paper/2407.11082/) (2024)
- [Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts](https://mlsanity.com/paper/2602.06859/) (2026)

## Abstract (arXiv)

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 set. Due to the scarcity of research on the work of graph-level anomaly detection, the detailed description of graph-level anomaly is insufficient. Furthermore, existing works focus on capturing anomalous graph information to learn better graph representations, but they ignore the importance of an effective anomaly score function for evaluating abnormal graphs. Thus, in this work, we first define anomalous graph information including node and graph property anomalies in a graph set and adopt node-level and graph-level information differences to identify them, respectively. Then, we introduce a discriminative graph-level anomaly detection framework with dual-students-teacher model, where the teacher model with a heuristic loss are trained to make graph representations more divergent. Then, two competing student models trained by normal and abnormal graphs respectively fit graph representations of the teacher model in terms of node-level and graph-level representation perspectives. Finally, we combine representation errors between two student models to discriminatively distinguish anomalous graphs. Extensive experiment analysis demonstrates that our method is effective for the graph-level anomaly detection task on graph datasets in the real world.