Saved in:
Bibliographic Details
Main Authors: Matyash, Maximilian, Gal, Avigdor, Senderovich, Arik
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.22553
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918171501395968
author Matyash, Maximilian
Gal, Avigdor
Senderovich, Arik
author_facet Matyash, Maximilian
Gal, Avigdor
Senderovich, Arik
contents With recent technological advances, process logs, which were traditionally deterministic in nature, are being captured from non-deterministic sources, such as uncertain sensors or machine learning models (that predict activities using cameras). In the presence of stochastically-known logs, logs that contain probabilistic information, the need for stochastic trace recovery increases, to offer reliable means of understanding the processes that govern such systems. We design a novel deep learning approach for stochastic trace recovery, based on Diffusion Denoising Probabilistic Models (DDPM), which makes use of process knowledge (either implicitly by discovering a model or explicitly by injecting process knowledge in the training phase) to recover traces by denoising. We conduct an empirical evaluation demonstrating state-of-the-art performance with up to a 25% improvement over existing methods, along with increased robustness under high noise levels.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22553
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DDTR: Diffusion Denoising Trace Recovery
Matyash, Maximilian
Gal, Avigdor
Senderovich, Arik
Machine Learning
Artificial Intelligence
With recent technological advances, process logs, which were traditionally deterministic in nature, are being captured from non-deterministic sources, such as uncertain sensors or machine learning models (that predict activities using cameras). In the presence of stochastically-known logs, logs that contain probabilistic information, the need for stochastic trace recovery increases, to offer reliable means of understanding the processes that govern such systems. We design a novel deep learning approach for stochastic trace recovery, based on Diffusion Denoising Probabilistic Models (DDPM), which makes use of process knowledge (either implicitly by discovering a model or explicitly by injecting process knowledge in the training phase) to recover traces by denoising. We conduct an empirical evaluation demonstrating state-of-the-art performance with up to a 25% improvement over existing methods, along with increased robustness under high noise levels.
title DDTR: Diffusion Denoising Trace Recovery
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.22553