The paper introduces two novel techniques for enhancing graph neural networks on Petri nets: a positional encoding derived from directed place‑transition walk return probabilities (PNRWPE) and a diffusion‑kernel‑based message gating using the incidence matrix (DA‑PNGNN). These methods explicitly capture directed cycles and invariants that were previously hidden, leading to significant performance gains. On the Process Discovery Contest 2023 dataset, PNRWPE raises macro balanced accuracy from 0.751 to 0.796, nearly doubling loop detection accuracy, while DA‑PNGNN further improves it to 0.830 and boosts net‑to‑tree retrieval on ProcRosetta by 4.1–5.9 points.
arXiv:2610.17702v1 Announce Type: new Abstract: Evaluating the quality of process models discovered from event logs is a fundamental challenge in process mining. Traditional evaluation relies on conf...
The paper presents a model‑centric evaluation framework for process discovery that uses node embeddings and Procrustes alignment to compare Petri net models across different datasets. By transforming Petri nets into graph representations, the method computes a bounded cosine‑distance metric that unifies fitness and precision assessments and remains robust to noise. Experiments on real and synthetic logs demonstrate that the embedding‑based indicator outperforms traditional conformance metrics and is sensitive to model degradation while providing activity‑level deviation localization.
arXiv:2608. 09398v1 Announce Type: cross Abstract: Process discovery is one of the central challenges in process mining.
arXiv:2606. 14283v1 Announce Type: cross Abstract: Deep learning has driven many recent advances in process analytics, especially for predictive and prescriptive monitoring.
arXiv:2609.08622v1 Announce Type: cross Abstract: Predictive process monitoring aims at forecasting various aspects of running processes. Among the different tasks, next activity prediction represent...
arXiv:2412. 00508v2 Announce Type: replace-cross Abstract: Control structure design is an important but tedious step in P&ID development.
arXiv:2609.14534v1 Announce Type: new Abstract: Predictive Process Monitoring (PPM) aims at predicting at runtime and as early as possible the future states of a process execution. Common tasks inclu...
The paper introduces SPICE, a Python framework that reimplements three popular deep‑learning methods for Predictive Process Mining (PPM) using PyTorch. It provides a common, highly configurable base to enable reproducible and robust comparison of PPM models, addressing issues of reproducibility, transparency, and usability. The authors benchmark SPICE against the original reported metrics and fair metrics across 11 datasets.
arXiv:2507. 22524v3 Announce Type: replace Abstract: We propose HGCN(O), a self-tuning toolkit using Graph Convolutional Network (GCN) models for event sequence prediction.
DeltaGNN introduces an information flow control mechanism that uses a new connectivity measure, the information flow score, to mitigate over‑smoothing and over‑squashing in Graph Neural Networks. This approach enables linear computational and memory overhead while effectively capturing both short‑range and long‑range node interactions. Experiments on ten diverse real‑world datasets demonstrate superior performance with limited computational complexity.
arXiv:2607. 04856v1 Announce Type: new Abstract: Local Process Models (LPMs) are an underexplored concept in process mining.
arXiv:2306.11313v5 Announce Type: replace-cross Abstract: Point process models are widely used for continuous-time discrete-event data, where each data point includes time and additional information...