Technology Category
Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, TrustReasoning under Uncertainty: Stochastic OptimizationMachine Learning: Probabilistic Circuits and Graphical Models
DDTR: Diffusion Denoising Trace Recovery
🤖 AI Summary
Existing trajectory recovery methods lack robustness under high noise when applied to stochastic process logs generated by nondeterministic data sources (e.g., noisy sensors or probabilistic AI models). This paper introduces, for the first time, diffusion denoising probabilistic models (DDPMs) into process mining, proposing a stochastic trajectory recovery method that jointly leverages explicit and implicit process knowledge. Specifically, it conditions the denoising process on trajectory distributions and incorporates process constraints to guide sampling, enabling reliable reconstruction of deterministic behavioral traces from probabilistic logs. The core innovation lies in a process-knowledge-driven diffusion framework, which significantly enhances noise robustness and recovery accuracy. Experiments across diverse noise scenarios demonstrate that the proposed method achieves an average 25% improvement in recovery accuracy over state-of-the-art approaches, along with markedly increased stability.
Technology Category
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
Recovering stochastic traces from probabilistic process logs
Denoising uncertain sensor and ML-generated activity data
Improving reliability of process understanding in non-deterministic systems
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses diffusion denoising probabilistic models for recovery
Leverages process knowledge through model discovery or injection
Demonstrates improved performance and robustness under noise
🔎 Similar Papers
No similar papers found.
