Abstract
The only constant is change. Drift detection in process mining is a family of methods to detect changes by analyzing event logs to ensure the accuracy and reliability of business processes in process-aware information systems (e.g., ERP systems). However, artificial feature selection is still a mountain to climb in existing methods, which requires high domain knowledge for users. In this paper, we propose a novel approach by using Graph convolutional networks for Drifts Detection in the event log, we name it GDD. Specifically, 1) we transform event sequences into two directed graphs by using two consecutive time windows, and construct the line graphs for the directed graphs to capture the orders between different activities; 2) we use graph convolutional networks to capture the features in these graphs, and augment the original graphs with virtual nodes to represent the latent aspects of the graphs; 3) we calculate the distances between virtual nodes, and use the K-means algorithm to find the outliers that are considered as candidate change points. Then, a filter mechanism is used to confirm the actual change points. The experiments on simulated event logs and real-life event logs confirmed the improvements of GDD compared with the baselines.
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
Similar content being viewed by others
References
van der Aalst, W.M.P.: Process Mining: Discovery, Conformance and Enhancement of Business Processes. Springer, New York (2011)
Leemans, S.J.J., Fahland, D., van der Aalst, W.M.P.: Discovering block-structured process models from event logs containing infrequent behaviour. In: Lohmann, N., Song, M., Wohed, P. (eds.) BPM 2013. LNBIP, vol. 171, pp. 66–78. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-06257-0_6
Guo, Q., Wen, L., Wang, J., Yan, Z., Yu, P.S.: Mining invisible tasks in non-free-choice constructs. In: Motahari-Nezhad, H.R., Recker, J., Weidlich, M. (eds.) BPM 2015. LNCS, vol. 9253, pp. 109–125. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23063-4_7
Sander, J.J., Leemans, A.F.S., Aalst, W.M.P.: Earth moves’ stochastic conformance checking. In: International Conference on Business Process Management. Vienna, Austria, pp. 127–143 (2019)
Fahland, D., Aalst, W.M.P.: Model repair - aligning process models to reality. Inf. Syst. 47(1), 220–243 (2015)
Bose, R.P.J.C., Aalst, W.M.P., et al.: Dealing with concept drifts in process mining. IEEE Trans. Neural Netw. Learn. Syst. 25(1), 154–171 (2014)
Bose, R.P.J.C., van der Aalst, W.M.P., Žliobaitė, I., Pechenizkiy, M.: Handling concept drift in process mining. In: Mouratidis, H., Rolland, C. (eds.) CAiSE 2011. LNCS, vol. 6741, pp. 391–405. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21640-4_30
Maaradji, A., Dumas, M., La Rosa, M., Ostovar, A.: Fast and accurate business process drift detection. In: Motahari-Nezhad, H.R., Recker, J., Weidlich, M. (eds.) BPM 2015. LNCS, vol. 9253, pp. 406–422. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-23063-4_27
Ostovar, A., Maaradji, A., Rosa, M.L., et al.: Detecting drift from event streams of unpredictable business processes. In: International Conference on Conceptual Modeling. Gifu, Japan, pp. 330–346 (2016)
Ostovar, A., Leemans, S., Rosa, M.L.: Robust drift characterization from event streams of business processes. ACM Trans. Knowl. Disc. Data 14(3), 1–57 (2020)
Zheng, C., Wen, L., Wang, J.: Detecting process concept drifts from event logs. In: Panetto, H., et al. (eds.) OTM 2017. LNCS, vol. 10573, pp. 524–542. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-69462-7_33
Lu, Y., Chen, Q., Poon, S.: A robust and accurate approach to detect process drifts from event streams. In: Polyvyanyy, A., Wynn, M.T., Van Looy, A., Reichert, M. (eds.) BPM 2021. LNCS, vol. 12875, pp. 383–399. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-85469-0_24
Widmer, G., Kubat, M.: Learning in the presence of concept drift and hidden contexts. Mach. Learn. 23(1), 69–101 (1996)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: The 5th International Conference on Learning Representations. Toulon, France, pp. 1–14 (2017)
Maggi, F.M., Burattin, A., Cimitile, M., Sperduti, A.: Online process discovery to detect concept drifts in LTL-based declarative process models. In: Meersman, R., et al. (eds.) OTM 2013. LNCS, vol. 8185, pp. 94–111. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-41030-7_7
Lin, L., Wen, L., Lin, L., Pei, J., Yang, H.: LCDD: detecting business process drifts based on local completeness. IEEE Trans. Serv. Comput. 15(4), 2086–2099 (2022)
Carmona, J., Gavaldà, R.: Online techniques for dealing with concept drift in process mining. In: Hollmén, J., Klawonn, F., Tucker, A. (eds.) IDA 2012. LNCS, vol. 7619, pp. 90–102. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-34156-4_10
Kumar, M.V.M., Thomas, L., Annappa, B.: Capturing the sudden concept drift in process mining, pp. 132–143. Algorithms Theories Anal. Event Data, Brussels, Belgium (2015)
Yeshchenko, A., Di Ciccio, C., Mendling, J., et al.: Visual drift detection for sequence data analysis of business processes. IEEE Trans. Vis. Comput. Graph. (2021). https://doi.org/10.1109/TVCG.2021.3050071
Jiang, X., Ji, P., Li, S.: CensNet: convolution with edge-node switching in graph neural networks. In: International Joint Conferences on Artificial Intelligence (IJCAI), pp. 2656–2662 (2019)
Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710 (2014)
Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: The Association for the Advancement of Artificial Intelligence (AAAI), pp. 2786–2792 (2016)
Pham, T., Tran, T., Dam, H., Venkatesh, S.: Graph classification via deep learning with virtual nodes. arXiv:1708.04357 (2017)
Acknowledgements
The work was supported by the National Key Research and Development Program of China (2018YFB1800403), the general project numbered KM202310028003 of Beijing Municipal Education Commission, the National Natural Science Foundation of China (61872252).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, L. et al. (2023). Process Drift Detection in Event Logs with Graph Convolutional Networks. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13946. Springer, Cham. https://doi.org/10.1007/978-3-031-30678-5_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-30678-5_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30677-8
Online ISBN: 978-3-031-30678-5
eBook Packages: Computer ScienceComputer Science (R0)