Skip to main content
SpringerLink
Log in

One-class graph neural networks for anomaly detection in attributed networks

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Nowadays, graph-structured data are increasingly used to model complex systems. Meanwhile, detecting anomalies from graph has become a vital research problem of pressing societal concerns. Anomaly detection is an unsupervised learning task of identifying rare data that differ from the majority. As one of the dominant anomaly detection algorithms, one-class support vector machine has been widely used to detect outliers. However, those traditional anomaly detection methods lost their effectiveness in graph data. Since traditional anomaly detection methods are stable, robust and easy to use, it is vitally important to generalize them to graph data. In this work, we propose one-class graph neural network (OCGNN), a one-class classification framework for graph anomaly detection. OCGNN is designed to combine the powerful representation ability of graph neural networks along with the classical one-class objective. Compared with other baselines, OCGNN achieves significant improvements in extensive experiments.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. https://github.com/WangXuhongCN/OCGNN.

  2. https://github.com/WangXuhongCN/OCGNN.

References

  1. Akoglu L, Tong H, Koutra D (2015) Graph based anomaly detection and description: a survey. Data Min Knowl Discov 29(3):626–688

    Article  MathSciNet  Google Scholar 

  2. Bresson X, Laurent T (2017) Residual gated graph convnets. CoRR arXiv:1711.07553

  3. Breunig MM, Kriegel H, Ng RT, Sander J (2000) LOF: identifying density-based local outliers. In: ACM SIGMOD international conference on management of data (SIGMOD), ACM, pp 93–104

  4. Candès EJ, Li X, Ma Y, Wright J (2011) Robust principal component analysis? J ACM 58(3):11:1–11:37

    Article  MathSciNet  Google Scholar 

  5. Chen J, Sathe S, Aggarwal CC, Turaga DS (2017) Outlier detection with autoencoder ensembles. In: SDM, SIAM, pp 90–98

  6. Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: NeurIPS, pp 3837–3845

  7. Ding K, Li J, Bhanushali R, Liu H (2019) Deep anomaly detection on attributed networks. In: SDM, SIAM, pp 594–602

  8. Gao J, Liang F, Fan W, Wang C, Sun Y, Han J (2010) On community outliers and their efficient detection in information networks. In: KDD, ACM, pp 813–822

  9. Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: AISTATS, JMLR.org, vol 9, pp 249–256

  10. Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville AC, Bengio Y (2014) Generative adversarial nets. In: Annual conference on neural information processing systems (NeurIPS). MIT Press, pp 2672–2680

  11. Hamilton WL, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. In: NIPS, pp 1024–1034

  12. Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: International conference on learning representations (ICLR)

  13. Kipf TN, Welling M (2016) Variational graph auto-encoders. CoRR arXiv:1611.07308

  14. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: ICLR (Poster), OpenReview.net

  15. Li J, Dani H, Hu X, Liu H (2017) Radar: residual analysis for anomaly detection in attributed networks. In: IJCAI, ijcai.org, pp 2152–2158

  16. Li Y, Huang X, Li J, Du M, Zou N (2019) Specae: spectral autoencoder for anomaly detection in attributed networks. In: CIKM, ACM, pp 2233–2236

  17. Liu FT, Ting KM, Zhou Z (2008) Isolation forest. In: ICDM. IEEE Computer Society, pp 413–422

  18. Liu Y, Li Z, Zhou C, Jiang Y, Sun J, Wang M, He X (2020) Generative adversarial active learning for unsupervised outlier detection. IEEE Trans Knowl Data Eng 32(8):1517–1528

    Article  Google Scholar 

  19. Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: ICLR

  20. Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605

    MATH  Google Scholar 

  21. Olive DJ (2017) Principal component analysis. Springer, New York, pp 189–217

    Google Scholar 

  22. Peng H, Li J, Gong Q, Song Y, Ning Y, Lai K, Yu PS (2019) Fine-grained event categorization with heterogeneous graph convolutional networks. In: IJCAI, ijcai.org, pp 3238–3245

  23. Peng Z, Luo M, Li J, Liu H, Zheng Q (2018) ANOMALOUS: a joint modeling approach for anomaly detection on attributed networks. In: IJCAI, ijcai.org, pp 3513–3519

  24. Perozzi B, Akoglu L (2016) Scalable anomaly ranking of attributed neighborhoods. In: SDM, SIAM, pp 207–215

  25. Perozzi B, Akoglu L, Sánchez PI, Müller E (2014a) Focused clustering and outlier detection in large attributed graphs. In: KDD, ACM, pp 1346–1355

  26. Perozzi B, Al-Rfou R, Skiena S (2014b) Deepwalk: online learning of social representations. In: KDD, ACM, pp 701–710

  27. Pimentel MAF, Clifton DA, Clifton LA, Tarassenko L (2014) A review of novelty detection. Signal Process 99:215–249

    Article  Google Scholar 

  28. Ribeiro LFR, Saverese PHP, Figueiredo DR (2017) struc2vec: learning node representations from structural identity. In: KDD, ACM, pp 385–394

  29. Ruff L, Görnitz N, Deecke L, Siddiqui SA, Vandermeulen RA, Binder A, Müller E, Kloft M (2018) Deep one-class classification. ICML, PMLR, Proc Mach Learn Res 80:4390–4399

    Google Scholar 

  30. Sánchez PI, Müller E, Laforet F, Keller F, Böhm K (2013) Statistical selection of congruent subspaces for mining attributed graphs. In: ICDM, IEEE Computer Society, pp 647–656

  31. Sen P, Namata G, Bilgic M, Getoor L, Gallagher B, Eliassi-Rad T (2008) Collective classification in network data. AI Maga 29(3):93–106

    Article  Google Scholar 

  32. Tax DMJ, Duin RPW (2004) Support vector data description. Mach Learn 54(1):45–66

    Article  Google Scholar 

  33. Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2018) Graph attention networks. In: ICLR (Poster), OpenReview.net

  34. Wang C, Wang J, Wang C, Shen Q (2018) Actor model anomaly detection using kernel principal component analysis. In: ICONIP (4), Lecture Notes in Computer Science, vol 11304. Springer, pp 545–554

  35. Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: KDD, ACM, pp 1225–1234

  36. Wang D, Qi Y, Lin J, Cui P, Jia Q, Wang Z, Fang Y, Yu Q, Zhou J, Yang S (2019a) A semi-supervised graph attentive network for financial fraud detection. In: ICDM, IEEE, pp 598–607

  37. Wang M, Yu L, Zheng D, Gan Q, Gai Y, Ye Z, Li M, Zhou J, Huang Q, Ma C, Huang Z, Guo Q, Zhang H, Lin H, Zhao J, Li J, Smola AJ, Zhang Z (2019b) Deep graph library: towards efficient and scalable deep learning on graphs. In: ICLR workshop on representation learning on graphs and manifolds

  38. Wang X, Du Y, Lin S, Cui P, Shen Y, Yang Y (2020) advae: a self-adversarial variational autoencoder with gaussian anomaly prior knowledge for anomaly detection. Knowl Based Syst 190:105187

  39. Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi K, Jegelka S (2018) Representation learning on graphs with jumping knowledge networks. ICML, PMLR, Proc Mach Learn Res 80:5449–5458

    Google Scholar 

  40. Xu K, Hu W, Leskovec J, Jegelka S (2019) How powerful are graph neural networks? In: ICLR, OpenReview.net

  41. Yu B, Yin H, Zhu Z (2018) Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In: IJCAI, ijcai.org, pp 3634–3640

  42. Zhang H, Wang S, Xu X, Chow TWS, Wu QMJ (2018) Tree2vector: learning a vectorial representation for tree-structured data. IEEE Trans Neural Netw Learn Syst 29(11):5304–5318

    Article  MathSciNet  Google Scholar 

  43. Zhou C, Paffenroth RC (2017) Anomaly detection with robust deep autoencoders. In: KDD, ACM, pp 665–674

Download references

Acknowledgements

This research is supported by National Natural Science Foundation of China (Nos. 51777122 and 61273161). This work is also supported by the National Research Foundation of Singapore through a grant to the Berkeley Education Alliance for Research in Singapore (BEARS) for the Singapore-Berkeley Building Efficiency and Sustainability in the Tropics (SinBerBEST) program, and by the Defence Science & Technology Agency (DSTA) of Singapore.

Author information

Authors and Affiliations

  1. The Ministry of Education Key Laboratory of System Control and Information Processing, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China

    Xuhong Wang, Ying Du, Ping Cui & Yupu Yang

  2. Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA

    Baihong Jin & Yingshui Tan

Authors
  1. Xuhong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Baihong Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ying Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ping Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yingshui Tan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yupu Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xuhong Wang.

Ethics declarations

Conflicts of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, X., Jin, B., Du, Y. et al. One-class graph neural networks for anomaly detection in attributed networks. Neural Comput & Applic 33, 12073–12085 (2021). https://doi.org/10.1007/s00521-021-05924-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-05924-9

Keywords

Search

Navigation