发表机构
Department of Computer Science, Brock University; School of Electrical Engineering and Computer Science, University of Ottawa; Ciena Corporation（布罗克大学计算机科学系; Ottawa 大学电气工程与计算机科学学院; Ciena 公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对工业系统收集内核执行跟踪成本高的问题，提出TraceSynth框架，利用基于Transformer的去噪扩散过程及约束引导修复生成合成内核跟踪，在六个基准测试中验证效果，显示其能经济高效增强跟踪并助于判断合成数据替代真实跟踪的时机。
AI 中文摘要
用于系统诊断的机器学习模型依赖内核执行跟踪来捕获细粒度系统行为，但在工业系统中收集生产跟踪因运行时开销、存储需求和隐私限制而成本高昂。我们提出了TraceSynth，一个基于扩散的框架，用于生成合成内核跟踪，以增强有限的真实数据用于下游机器学习任务。TraceSynth使用基于Transformer的去噪扩散过程，将跟踪建模为多通道序列，并通过约束引导修复来强化系统不变量。在六个基准测试中，结果显示出强烈的工作负载依赖性。对于确定性、计算量大的工作负载（scimark2），在上下文长度L = 4096时，合成增强实现了87.2%的F1-Macro，仅比仅使用真实数据的基线低2.6个百分点。上下文长度是主要的质量因素，L = 4096比L = 256产生了104%的相对改进，而约束引导修复将合成数据质量提高了4.3%。消融研究表明，轻量级的2通道模型以大约一半的计算成本保留了全6通道模型97 - 99%的性能。TraceSynth支持在生产可观测性管道中经济高效地增强内核执行跟踪，并有助于确定何时合成数据可以替代有限的真实跟踪。
英文摘要
Machine learning models for system diagnostics rely on kernel execution traces to capture fine-grained system behavior, but collecting production traces in industrial systems is costly due to runtime overhead, storage demands, and privacy constraints. We present TraceSynth, a diffusion-based framework for generating synthetic kernel traces that augment limited real data for downstream ML tasks. TraceSynth models traces as multi-channel sequences (event types, timestamps, CPU affinity, thread identifiers, and process metadata) using a Transformer-based denoising diffusion process with constraint-guided repair to enforce system invariants. Across six benchmarks, results show strong workload dependence. For deterministic, compute-heavy workloads (scimark2), synthetic augmentation achieves 87.2% F1-Macro at context length L=4096, only 2.6 percentage points below real-only baselines. Context length is the dominant quality factor, with L=4096 yielding a +104% relative improvement over L=256, while constraint-guided repair improves synthetic data quality by up to 4.3%. Ablation studies show that lightweight 2-channel models retain 97-99% of the performance of full 6-channel models at roughly half the computational cost. TraceSynth supports cost-effective augmentation of kernel execution traces in production observability pipelines and helps identify when synthetic data can substitute for limited real traces.
Comments11 pages, 2 figures, 6 tables. Author's accepted version. Published in the Industry Track of the 34th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE Companion '26), Montreal, QC, Canada. Code: https://github.com/17YuvrajSehgal/SyntheticLogGeneration
Journal refFSE Companion '26: Companion Proceedings of the 34th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, Montreal, QC, Canada, 2026
