Message passing improves prediction accuracy for petri net process models
Structure-Aware Message Passing on Petri Nets through Directed Walks and Incidence Diffusion
Machine LearningArtificial Intelligence
Summary
Petri nets are a way to represent processes with events and stages, often used to understand workflows. The authors found that current methods overlook important structural details like loops and rules embedded in these nets. They designed new techniques to help machine learning models better recognize these features by analyzing directed paths and connectivity information. Their approach significantly improved the accuracy of predicting process behaviors and retrieving related process models.
What this means in practice
- •For process analysts: Improve the accuracy of identifying process structures and loops from event logs by using enhanced Petri net representations.
- •For workflow automation teams: Retrieve and match process models more effectively to optimize automated workflows based on event data.
Authors
Geri Skenderi
Abstract
A common application of the process mining discipline is to connect observed event data with Petri nets, which are bipartite, directed graphical process models with rich formal underpinnings. Recent work learns vector representations of Petri nets to retrieve process models and relate them to event logs, but leaves implicit two key aspects hidden within the net's structure: directed cycles (process loops) and invariants recorded by the net's incidence matrix. We expose both of these to message-passing graph neural networks, through a positional encoding built from return probabilities of directed place-transition walks (PNRWPE), and through same-type messages gated by diffusion kernels of the incidence matrix (DA-PNGNN). Our constructions raise macro balanced accuracy in predicting the generation factors of the 96 Process Discovery Contest 2023 models from 0.751 to 0.796 with PNRWPE, which nearly doubles accuracy on process loops, and to 0.830 with DA-PNGNN, which, without retuning, also improves net-to-tree retrieval top-1 accuracy on the self-supervised ProcRosetta benchmark by 4.1 to 5.9 points.