Execution Trace Reconstruction Using Diffusion-Based Generative Models
Madeline Janecek, Naser Ezzati-Jivan, Abdelwahab Hamou-Lhadj
Abstract
Execution tracing is essential for understanding system and software behaviour, yet lost trace events can significantly compromise data integrity and analysis. Existing solutions for trace reconstruction often fail to fully leverage available data, particularly in complex and high-dimensional contexts. Recent advancements in generative artificial intelligence, particularly diffusion models, have set new benchmarks in image, audio, and natural language generation. This study conducts the first comprehensive evaluation of diffusion models for reconstructing incomplete trace event sequences. Using nine distinct datasets generated from the Phoronix Test Suite, we rigorously test these models on sequences of varying lengths and missing data ratios. Our results indicate that the SSSD<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</sup><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> model, in particular, achieves superior performance, in terms of accuracy, perfect rate, and ROUGE-L score across diverse imputation scenarios. These findings underscore the potential of diffusion-based models to accurately reconstruct missing events, thereby maintaining data integrity and enhancing system monitoring and analysis.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation cites DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Diffusion Models Beat GANs on Image Synthesis cites DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Diffusion Models Beat GANs on Image Synthesis
Builds on9
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
- Efficiently Modeling Long Sequences with Structured State SpacesAlbert Gu, Karan Goel, Christopher RéICLR 2022 · 3,482 citations
- DiffWave: A Versatile Diffusion Model for Audio SynthesisZhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao et al.ICLR 2021 · 1,902 citations
- CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series ImputationYusuke Tashiro, Jiaming Song, Yang Song, Stefano ErmonNeurIPS 2021 · 1,245 citations
Related papers
- TRACE: Trajectory Recovery with State Propagation Diffusion for Urban MobilityJinming Wang, Hai Wang, Hongkai Wen, Geyong Min et al.WWW 2026
- Generative Human Trajectory Recovery via Embedding-Space Conditional DiffusionKaijun Liu, Sijie Ruan, Liang Zhang, Cheng Long et al.ICML 2025
- DiffPuter: Empowering Diffusion Models for Missing Data ImputationHengrui Zhang, Liancheng Fang, Qitian Wu, Philip S. YuICLR 2025
- Incomplete Data, Complete Dynamics: A Diffusion ApproachZihan Zhou, Chenguang Wang, Hongyi Ye, Yongtao Guan et al.ICLR 2026 · 3 citations
- Event-Guided HDR Reconstruction with Diffusion PriorsYixin Yang, Jiawei Zhang, Yang Zhang, Yunxuan Wei et al.ICCV 2025 · 4 citations
