Process Discovery Using Graph Neural Networks

TL;DR

This paper introduces a supervised learning approach using graph neural networks to improve process discovery from event logs, enabling the translation of logs into sound Petri nets with comparable accuracy to existing methods.

Contribution

It presents a novel ML-based process discovery method trained on synthetic data, reducing biases of heuristic-based algorithms and handling diverse process models.

Findings

The method accurately translates unseen logs into sound Petri nets.

It performs comparably to state-of-the-art techniques on real-life logs.

The approach demonstrates the potential of supervised learning in process mining.

Abstract

Automatically discovering a process model from an event log is the prime problem in process mining. This task is so far approached as an unsupervised learning problem through graph synthesis algorithms. Algorithmic design decisions and heuristics allow for efficiently finding models in a reduced search space. However, design decisions and heuristics are derived from assumptions about how a given behavioral description - an event log - translates into a process model and were not learned from actual models which introduce biases in the solutions. In this paper, we explore the problem of supervised learning of a process discovery technique D. We introduce a technique for training an ML-based model D using graph convolutional neural networks; D translates a given input event log into a sound Petri net. We show that training D on synthetically generated pairs of input logs and output models allows D to translate previously unseen synthetic and several real-life event logs into sound, arbitrarily structured models of comparable accuracy and simplicity as existing state of the art techniques for discovering imperative process models. We analyze the limitations of the proposed technique and outline alleys for future work.