Exploring gated graph sequence neural networks for predicting next process activities
Weinzierl S (2021)
Publication Type: Conference contribution, Conference Contribution
Publication year: 2021
Publisher: Springer
Pages Range: 30-42
Conference Proceedings Title: Proceedings of the BPM 2021 International Workshops.
Event location: Rom
DOI: 10.1007/978-3-030-94343-1_3
Abstract
A current trend in predictive business process monitoring is to construct predictive models using deep neural networks (DNNs), especially long
short-term memory neural networks, convolutional neural networks, or multilayer perceptron neural networks. While these DNN types typically require data
defined on the Euclidean space (e.g., grids), graph neural networks (GNNs), a relatively new type of DNNs, can compute data defined on the non-Euclidean space
(e.g., graphs). Because GNNs can directly compute graph-oriented data inputs,
generally structured into nodes and edges, they can explicitly model event relationships. This paper investigates gated graph sequence neural networks (GGNNs)
for the next activity prediction. First results with two real-life event logs show that
GGNNs can outperform traditional DNNs regarding predictive quality, especially
if nodes of an input graph are assumed as events, and the graph’s adjacency matrix only describes event relationships of a process instance prefix.
Authors with CRIS profile
How to cite
APA:
Weinzierl, S. (2021). Exploring gated graph sequence neural networks for predicting next process activities. In Proceedings of the BPM 2021 International Workshops. (pp. 30-42). Rom, IT: Springer.
MLA:
Weinzierl, Sven. "Exploring gated graph sequence neural networks for predicting next process activities." Proceedings of the International Conference on Business Process Management, Rom Springer, 2021. 30-42.
BibTeX: Download