CoChat
Sign Up
Cited by 86Advanced Graph Neural NetworksAnomaly Detection Techniques and ApplicationsGraph Theory and Algorithms

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation

Open access
Ma, Rongrong, Pang, Guansong, Chen, Ling, van den Hengel, Anton·2022·Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
DOI 10.1145/3488560.3498473
Open this paper in CoChat — free accountOpen PDF

Abstract

Graph-level anomaly detection (GAD) describes the problem of detecting graphs that are abnormal in their structure and/or the features of their nodes, as compared to other graphs. One of the challenges in GAD is to devise graph representations that enable the detection of both locally- and globally-anomalous graphs, i.e., graphs that are abnormal in their fine-grained (node-level) or holistic (graph-level) properties, respectively. To tackle this challenge we introduce a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations. The random distillation is achieved by training one GNN to predict another GNN with randomly initialized network weights. Extensive experiments on 16 real-world graph datasets from diverse domains show that our model significantly outperforms seven state-of-the-art models. Code and datasets are available at https://git.io/GLocalKD.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3488560.3498473

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Most existing surveys focus on homogeneous or static graphs, offering limited insight into models tailored for heterogeneous and dynamic graphs.

    “Moreover, most existing surveys [5], [6], [7], [8] focus on homogeneous or static graphs, offering limited insight into models tailored for heterogeneous and dynamic graphs.”

    From A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection (2025) · cites this paper as [7]

    Section 2.1 (pp. 2–3) discusses studies of time-evolving and static graph-level anomaly detection, but does not assess what most existing surveys cover. A search for survey coverage of homogeneous, heterogeneous, static, and dynamic graphs found no passage supporting the attributed claim. (LLM, conf=0.75)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 50

  1. Charu C Aggarwal and Haixun Wang. 2010. Graph data management and mining: a survey of algorithms and applications. In Managing and Mining Graph Data . Springer, 13--68.
  2. 10.1007/s10618-014-0365-y · DOI · Paper page
  3. Paul Bergmann Michael Fauser David Sattlegger and Carsten Steger. 2020. Uninformed students: student-teacher anomaly detection with discriminative latent embeddings. In CVPR. 4183--4192. · DOI · Paper page
  4. Yuri Burda, Harrison Edwards, Amos Storkey, and Oleg Klimov. 2018. Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018). · arXiv
  5. 10.1007/s10618-015-0444-8 · DOI
  6. Jinghui Chen, Saket Sathe, Charu Aggarwal, and Deepak Turaga. 2017. Outlier detection with autoencoder ensembles. In SDM. SIAM, 90--98.
  7. Kaize Ding Jundong Li Nitin Agarwal and Huan Liu. 2020. Inductive anomaly detection on attributed networks. In IJCAI. 1288--1294. · DOI
  8. Dhivya Eswaran Christos Faloutsos Sudipto Guha and Nina Mishra. 2018. Spotlight: detecting anomalies in streaming graphs. In KDD. 1378--1386. · DOI
  9. Mariana-Iuliana Georgescu, Antonio Barbalau, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, and Mubarak Shah. 2021. Anomaly detection in video via self-supervised and multi-task learning. In CVPR . 12742--12752.
  10. Simon Hawkins, Hongxing He, Graham Williams, and Rohan Baxter. 2002. Outlier detection using replicator neural networks. In DaWaK. Springer, 170--180.
  11. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015). · arXiv
  12. Jianguo Jiang, Jiuming Chen, Tianbo Gu, Kim-Kwang Raymond Choo, Chao Liu, Min Yu, Weiqing Huang, and Prasant Mohapatra. 2019. Anomaly detection with graph convolutional networks for insider threat and fraud detection. In MILCOM. IEEE, 109--114.
  13. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016). · arXiv
  14. Atsutoshi Kumagai, Tomoharu Iwata, and Yasuhiro Fujiwara. 2020. Semi-supervised anomaly detection on attributed graphs. arXiv preprint arXiv:2002.12011 (2020). · arXiv
  15. 10.1016/j.patcog.2020.107746 · DOI
  16. 10.1002/int.22389 · DOI
  17. 10.1109/JSTSP.2020.3001719 · DOI
  18. Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. 2008. Isolation forest. In ICDM. IEEE, 413--422.
  19. Emaad Manzoor Sadegh M Milajerdi and Leman Akoglu. 2016. Fast memory-efficient anomaly detection in streaming heterogeneous graphs. In KDD . 1035--1044. · DOI
  20. Annamalai Narayanan, Mahinthan Chandramohan, Rajasekar Venkatesan, Lihui Chen, Yang Liu, and Shantanu Jaiswal. 2017. Graph2vec: learning distributed representations of graphs. arXiv preprint arXiv:1707.05005 (2017). · arXiv
  21. 10.1007/s10994-015-5517-9 · DOI
  22. Phuc Cuong Ngo, Amadeus Aristo Winarto, Connie Khor Li Kou, Sojeong Park, Farhan Akram, and Hwee Kuan Lee. 2019. Fence GAN: towards better anomaly detection. In ICTAI. IEEE, 141--148.
  23. Hung T Nguyen, Pierre J Liang, and Leman Akoglu. 2020. Anomaly detection in large labeled multi-graph databases. arXiv preprint arXiv:2010.03600 (2020). · arXiv
  24. Ian Osband, John Aslanides, and Albin Cassirer. 2018. Randomized prior functions for deep reinforcement learning. arXiv preprint arXiv:1806.03335 (2018). · arXiv
  25. Guansong Pang Longbing Cao Ling Chen and Huan Liu. 2018. Learning representations of ultrahigh-dimensional data for random distance-based outlier detection. In KDD. 2041--2050. · DOI
  26. 10.1145/3439950 · DOI · Paper page
  27. Guansong Pang Chunhua Shen and Anton van den Hengel. 2019. Deep anomaly detection with deviation networks. In KDD. 353--362. · DOI
  28. Guansong Pang, Kai Ming Ting, and David Albrecht. 2015. LeSiNN: detecting anomalies by identifying least similar nearest neighbours. In 2015 ICDMW. IEEE, 623--630.
  29. 10.1109/TIP.2019.2917862 · DOI · Paper page
  30. Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexander Binder, Emmanuel Müller, and Marius Kloft. 2018. Deep one-class classification. In ICML. PMLR, 4393--4402.
  31. Mohammadreza Salehi, Niousha Sadjadi, Soroosh Baselizadeh, Mohammad Hossein Rohban, and Hamid R Rabiee. 2020. Multiresolution knowledge distillation for anomaly detection. arXiv preprint arXiv:2011.11108 (2020). · arXiv
  32. 10.1016/j.media.2019.01.010 · DOI
  33. Bernhard Schölkopf, Robert Williamson, Alex Smola, John Shawe-Taylor, and John Platt. 1999. Support vector method for novelty detection. In NIPS, Vol. 12. 582--588.
  34. Nino Shervashidze, Pascal Schweitzer, Erik Jan Van Leeuwen, Kurt Mehlhorn, and Karsten M Borgwardt. 2011. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research , Vol. 12, 9 (2011).
  35. Kumar Sricharan and Kamalika Das. 2014. Localizing anomalous changes in time-evolving graphs. In ACM SIGMOD . 1347--1358. · DOI
  36. Fan-Yun Sun Jordan Hoffmann Vikas Verma and Jian Tang. 2019. InfoGraph: unsupervised and semi-supervised graph-Level representation learning via mutual information maximization. In ICLR .
  37. A Varfis, E Kotsakis, A Tsois, AV Donati, M Sjachyn, E Camossi, P Villa, T Dimitrova, and M Pellissier. 2011. ConTraffic: maritime container traffic anomaly detection. In MAD 2011 Workshop Proceedings . Citeseer, 113.
  38. Hu Wang Guansong Pang Chunhua Shen and Congbo Ma. 2020. Unsupervised Representation Learning by Predicting Random Distances. In IJCAI . · DOI
  39. Xuhong Wang, Baihong Jin, Ying Du, Ping Cui, Yingshui Tan, and Yupu Yang. 2021. One-class graph neural networks for anomaly detection in attributed networks. Neural Computing and Applications (2021), 1--13.
  40. RF Woolson. 2007. Wilcoxon signed-rank test. Wiley Encyclopedia of Clinical Trials (2007), 1--3.
  41. 10.3390/e23020201 · DOI
  42. Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018). · arXiv
  43. Minji Yoon Bryan Hooi Kijung Shin and Christos Faloutsos. 2019. Fast and accurate anomaly detection in dynamic graphs with a two-pronged approach. In KDD . 647--657. · DOI
  44. Wenchao Yu Wei Cheng Charu C Aggarwal Kai Zhang Haifeng Chen and Wei Wang. 2018. Netwalk: a flexible deep embedding approach for anomaly detection in dynamic networks. In KDD . 2672--2681. · DOI
  45. 10.1609/aaai.v32i1.11782 · DOI
  46. Ziwei Zhang, Peng Cui, and Wenwu Zhu. 2020. Deep learning on graphs: a survey. IEEE Transactions on Knowledge and Data Engineering (2020).
  47. Lingxiao Zhao and Leman Akoglu. 2020. On using classification datasets to evaluate graph outlier detection: peculiar observations and new insights. arXiv preprint arXiv:2012.12931 (2020). · arXiv
  48. Tong Zhao Chuchen Deng Kaifeng Yu Tianwen Jiang Daheng Wang and Meng Jiang. 2020. Error-Bounded Graph Anomaly Loss for GNNs. In CIKM. 1873--1882. · DOI
  49. Li Zheng Zhenpeng Li Jian Li Zhao Li and Jun Gao. 2019 a. AddGraph: anomaly detection in dynamic graph using attention-based temporal GCN. In IJCAI . 4419--4425. · DOI · Paper page
  50. Chong Zhou and Randy C Paffenroth. 2017. Anomaly detection with robust deep autoencoders. In KDD. 665--674. · DOI

Cited by

Sorted by citations

Metadata

Authors
Ma, R., Pang, G., Chen, L., & van den Hengel, A.
Affiliations
  • University of Technology Sydney (AU)
  • Singapore Management University (SG)
  • The University of Adelaide (AU)
ORCID
Venue
Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
Publisher
ACM
Published
2022-02-11
Pages
704-714
DOI
10.1145/3488560.3498473
OpenAlex
W4213224406
Cited by
86
References
3
Citations by year
2026: 16 · 2025: 24 · 2024: 17 · 2023: 23 · 2022: 6
FWCI
9.68
Type
conference paper
Language
en
Open access
Licence
www.acm.org/publications/policies/copyright_policy#Background (vor)
Locations
  • ACM International Conference on Web Search and Data Mining (WSDM) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion, other-oa)
  • Adelaide Research & Scholarship (AR&S) (University of Adelaide) (submittedVersion)
  • arXiv (Cornell University)
Funders
ARC (DP210101347)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
  • Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
  • Physical Sciences › Computer Science › Computational Theory and Mathematics › Graph Theory and Algorithms
Keywords
knowledge distillation, graph neural networks, graph representation learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review