DDTR: Diffusion Denoising Trace Recovery
This addresses the need for reliable trace recovery in systems with non-deterministic logs, such as those from uncertain sensors or machine learning models, offering a solution for understanding stochastic processes.
The paper tackles the problem of stochastic trace recovery from probabilistic process logs, introducing a novel deep learning approach based on Diffusion Denoising Probabilistic Models (DDPM) that leverages process knowledge to denoise and recover traces, achieving state-of-the-art performance with up to a 25% improvement over existing methods and increased robustness under high noise levels.
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.