arXiv cs.AI· Geri Skenderi·· 13 小时前AI 评分20
通过有向游走与关联矩阵扩散在 Petri 网上实现结构感知消息传递
Structure-Aware Message Passing on Petri Nets through Directed Walks and Incidence Diffusion
AI 导读
研究提出 PNRWPE 与 DA-PNGNN 两种方法，将 Petri 网中的有向环和关联矩阵不变量显式暴露给消息传递图神经网络。在预测 96 个 Process Discovery Contest 2023 模型生成因子的任务上，宏平均平衡准确率从 0.751 提升至 0.796（PNRWPE），DA-PNGNN 进一步达到 0.830，并在过程环上近乎翻倍。
正文 · 原文
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.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29725 [cs.LG] |
| (or arXiv:2610.29725v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29725 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Geri Skenderi [view email]
[v1]
Wed, 21 Oct 2026 13:31:05 UTC (301 KB)
来源：arXiv cs.AI · arxiv.org