# Graph-level Anomaly Detection via Hierarchical Memory Networks

arXiv: https://arxiv.org/abs/2307.00755 · HTML: https://mlsanity.com/paper/2307.00755/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 27 of 27)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Learning Memory-guided Normality for Anomaly Detection](https://mlsanity.com/paper/2003.13228/) (2020)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Graph-based Anomaly Detection and Description: A Survey](https://mlsanity.com/paper/1404.4679/) (2014)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [Deep Structured Energy Based Models for Anomaly Detection](https://mlsanity.com/paper/1605.07717/) (2016)
- [Propagation Kernels](https://mlsanity.com/paper/1410.3314/) (2014)
- [Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation](https://mlsanity.com/paper/2112.10063/) (2021)
- [On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insights](https://mlsanity.com/paper/2012.12931/) (2020)
- [GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection](https://mlsanity.com/paper/2211.04208/) (2022)
- [Raising the Bar in Graph-level Anomaly Detection](https://mlsanity.com/paper/2205.13845/) (2022)
- [Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection](https://mlsanity.com/paper/2306.00006/) (2023)
- [Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment](https://mlsanity.com/paper/2212.01096/) (2022)
- [Semi-supervised Anomaly Detection on Attributed Graphs](https://mlsanity.com/paper/2002.12011/) (2020)
- [Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks](https://mlsanity.com/paper/1803.01500/) (2018)
- [Learning to Generate with Memory](https://mlsanity.com/paper/1602.07416/) (2016)

## Built on by (most cited first, 16 of 16)

- [Deep Graph Anomaly Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2409.09957/) (2024)
- [Generative Semi-supervised Graph Anomaly Detection](https://mlsanity.com/paper/2402.11887/) (2024)
- [Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection](https://mlsanity.com/paper/2310.02861/) (2023)
- [Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy](https://mlsanity.com/paper/2410.20366/) (2024)
- [MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization](https://mlsanity.com/paper/2507.20562/) (2025)
- [FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-level Anomaly Detection](https://mlsanity.com/paper/2605.09428/) (2026)
- [HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.02057/) (2024)
- [Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.13251/) (2024)
- [HRGCN: Heterogeneous Graph-level Anomaly Detection with Hierarchical Relation-augmented Graph Neural Networks](https://mlsanity.com/paper/2308.14340/) (2023)
- [FANFOLD: Graph Normalizing Flows-driven Asymmetric Network for Unsupervised Graph-Level Anomaly Detection](https://mlsanity.com/paper/2407.00383/) (2024)
- [Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2410.21322/) (2024)
- [From Pixels to Graphs: Deep Graph-Level Anomaly Detection on Dermoscopic Images](https://mlsanity.com/paper/2508.11826/) (2025)
- [Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality](https://mlsanity.com/paper/2403.09039/) (2024)
- [GLADformer: A Mixed Perspective for Graph-level Anomaly Detection](https://mlsanity.com/paper/2406.00734/) (2024)
- [Robust Anomaly Detection with Graph Neural Networks using Controllability](https://mlsanity.com/paper/2507.13954/) (2025)
- [DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection](https://mlsanity.com/paper/2511.04086/) (2025)

## Abstract (arXiv)

Graph-level anomaly detection aims to identify abnormal graphs that exhibit deviant structures and node attributes compared to the majority in a graph set. One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole. To tackle this challenge, we propose a novel approach called Hierarchical Memory Networks (HimNet), which learns hierarchical memory modules -- node and graph memory modules -- via a graph autoencoder network architecture. The node-level memory module is trained to model fine-grained, internal graph interactions among nodes for detecting locally abnormal graphs, while the graph-level memory module is dedicated to the learning of holistic normal patterns for detecting globally abnormal graphs. The two modules are jointly optimized to detect both locally- and globally-anomalous graphs. Extensive empirical results on 16 real-world graph datasets from various domains show that i) HimNet significantly outperforms the state-of-art methods and ii) it is robust to anomaly contamination. Codes are available at: https://github.com/Niuchx/HimNet.