Abstract
In many data stream applications, there is a normal concept, and the objective is to identify normal and abnormal concepts by training only with normal concept instances. This scenario is known in the literature as one-class learning (OCL) for data streams. In this OCL scenario for data streams, we highlight two main gaps: (i) lack of methods based on graph neural networks (GNNs) and (ii) lack of interpretable methods. We introduce OPENCAST (One-class graPh autoENCoder for dAta STream), a new method for data streams based on OCL and GNNs. Our method learns representations while encapsulating the instances of interest through a hypersphere. OPENCAST learns low-dimensional representations to generate interpretability in the representation learning process. OPENCAST achieved state-of-the-art results for data streams in the OCL scenario, outperforming seven other methods. Furthermore, OPENCAST learns low-dimensional representations, generating interpretability in the representation learning process and results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
OCL is also called one-class classification in the literature, but this work chose to use the term OCL.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
Other methods based on OCSVM, IForest and LOF (methods presented in the Related Work section) do not share the source code or the link to the source code is broken or the code is not in python which was the language used in this work.
References
Agrawal, R., Imielinski, T., Swami, A.: Database mining: a performance perspective. IEEE Trans. Knowl. Data Eng. 5(6), 914–925 (1993)
Bifet, A., et al.: MOA: massive online analysis, a framework for stream classification and clustering. In: Proceedings of the First Workshop on Applications of Pattern Analysis. PMLR (2010)
Bo, D., Wang, X., Shi, C., Shen, H.: Beyond low-frequency information in graph convolutional networks. In: Proceedings of the Conference of AAAI (2021)
Cai, L., et al.: Structural temporal graph neural networks for anomaly detection in dynamic graphs. In: Proceedings of the International Conference on Information and Knowledge Management (2021)
Corso, G., Stark, H., Jegelka, S., Jaakkola, T., Barzilay, R.: Graph neural networks. Nat. Rev. Methods Primers 4(1), 17 (2024)
de Faria, E.R., Ponce de Leon Ferreira Carvalho, A.C., Gama, J.: Minas: multiclass learning algorithm for novelty detection in data streams. Data mining and knowledge discovery 30, 640–680 (2016)
Feng, Y., Chen, J., Liu, Z., Lv, H., Wang, J.: Full graph autoencoder for one-class group anomaly detection of IIOT system. Internet Things J. 9(21) (2022)
Gama, J., Sebastiao, R., Rodrigues, P.P.: On evaluating stream learning algorithms. Mach. Learn. 90, 317–346 (2013)
Gaudreault, J.G., Branco, P.: A systematic literature review of novelty detection in data streams: challenges and opportunities. ACM Comput. Surv. (2024)
Gôlo, M.P.S., De Moraes, M.I., Goularte, R., Marcacini, R.M.: On the use of early fusion operators on heterogeneous graph neural networks for one-class learning. In: Proceedings of the Brazilian Symposium on Multimedia and the Web, pp. 128–136 (2023)
Gôlo, M.P.S., Junior, J.G.B.M., Silva, D.F., Marcacini, R.M.: Olga: one-class graph autoencoder. arXiv preprint arXiv:2406.09131 (2024)
Haug, J., Broelemann, K., Kasneci, G.: Dynamic model tree for interpretable data stream learning. In: International Conference on Data Engineering. IEEE (2022)
Jin, G., et al.: Spatio-temporal graph neural networks for predictive learning in urban computing: a survey. IEEE Trans. Knowl. Data Eng. (2023)
Jodelka, O., Anagnostopoulos, C., Kolomvatsos, K.: Adaptive novelty detection over contextual data streams at the edge using one-class classification. In: International Conference on Information and Communication Systems. IEEE (2021)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. Stat 1050, 21 (2016)
Luan, S., et al.: Revisiting heterophily for graph neural networks. Adv. Neural. Inf. Process. Syst. 35, 1362–1375 (2022)
Ma, Y., Guo, Z., Ren, Z., Tang, J., Yin, D.: Streaming graph neural networks. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 719–728 (2020)
Mendelson, S., Lerner, B.: Online cluster drift detection for novelty detection in data streams. In: International Conference on Machine Learning and Applications. IEEE (2020)
Moro, S., Rita, P., Cortez, P.: Bank Marketing. UCI Repository (2012)
Na, G.S., Kim, D., Yu, H.: Dilof: effective and memory efficient local outlier detection in data streams. In: Proceedings of Knowledge Discovery and Data Mining (2018)
Onuki, E.K.T., Malucelli, A., Barddal, J.P.: A tool for measuring energy consumption in data stream mining. In: BR Conference on Intelligent Systems. Springer (2023)
Peng, X., Li, Y., Tsang, I.W., Zhu, H., Lv, J., Zhou, J.T.: Xai beyond classification: interpretable neural clustering. J. Mach. Learn. Res. (2022)
Pitonakova, L., Bullock, S.: The robustness-fidelity trade-off in grow when required neural networks performing continuous novelty detection. Neural Networks (2020)
Puerto-Santana, C., et al.: Asymmetric HMMs for online ball-bearing health assessments. Internet Things J. 9(20), 20160–20177 (2022)
de Souza, M.C., Nogueira, B.M., Rossi, R.G., Marcacini, R.M., Rezende, S.O.: A heterogeneous network-based positive and unlabeled learning approach to detect fake news. In: Brazilian Conference on Intelligent Systems. Springer (2021)
Spinosa, E.J., de Leon F. de Carvalho, A.P., Gama, J.: Olindda: a cluster-based approach for detecting novelty and concept drift in data streams. In: Proceedings of the 2007 ACM Symposium on Applied Computing, pp. 448–452 (2007)
Tang, J., Liao, R.: Graph neural networks for node classification. In: Graph Neural Networks: Foundations, Frontiers, and Applications, pp. 41–61 (2022)
Togbe, M.U., et al.: Anomaly detection for data streams based on isolation forest using Scikit-Multiflow. In: Gervasi, O., et al. (eds.) ICCSA 2020. LNCS, vol. 12252, pp. 15–30. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58811-3_2
Veloso, B., Gama, J., Malheiro, B., Vinagre, J.: Hyperparameter self-tuning for data streams. Inf. Fusion 76, 75–86 (2021)
Wang, X., Jin, B., Du, Y., Cui, P., Tan, Y., Yang, Y.: One-class graph neural networks for anomaly detection in attributed networks. Neural Comput. Appl. 33(18), 12073–12085 (2021). https://doi.org/10.1007/s00521-021-05924-9
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: Proceedings of the International Conference on Learning Representations. Open Review (2019)
Zhang, F., Fan, H., Wang, R., Li, Z., Liang, T.: Deep dual support vector data description for anomaly detection on attributed networks. Int. J. Intell. Syst. 37(2), 1509–1528 (2022)
Zheng, Y., Yi, L., Wei, Z.: A survey of dynamic graph neural networks. arXiv preprint arXiv:2404.18211 (2024)
Acknowledgments
This work was supported by Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) grant number 88887.671481/2022-00. Also, this work was supported by LatAm Google Ph.D. Fellowship. Finally, we would like to thank Google Tutor Mara Finkelstein for reviewing the work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Silva Gôlo, M.P., Gama, J., Marcondes Marcacini, R. (2025). One-Class Learning for Data Stream Through Graph Neural Networks. In: Paes, A., Verri, F.A.N. (eds) Intelligent Systems. BRACIS 2024. Lecture Notes in Computer Science(), vol 15415. Springer, Cham. https://doi.org/10.1007/978-3-031-79038-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-79038-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-79037-9
Online ISBN: 978-3-031-79038-6
eBook Packages: Computer ScienceComputer Science (R0)