DDTR: Diffusion Denoising Trace Recovery

TL;DR

This paper introduces DDTR, a deep learning method using diffusion denoising models to recover stochastic process traces from uncertain logs, significantly improving accuracy and robustness over existing techniques.

Contribution

The paper presents a novel diffusion-based deep learning approach for stochastic trace recovery that incorporates process knowledge to enhance performance.

Findings

Achieves up to 25% improvement over existing methods.

Demonstrates increased robustness under high noise conditions.

Provides state-of-the-art results in stochastic trace recovery.

Abstract

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.