English(EN) Process-Aware Event Log Augmentation for Process Prediction under Labeled Data Scarcity

新的自监督框架通过数据增强提升过程预测能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

研究人员开发了SiamSA-PPM，一个新颖的自监督框架，旨在改善在标记数据有限情况下的预测性过程监控（PPM）。该框架结合了Siamese学习和基于统计的数据增强，采用了考虑控制流语义和常见行为模式的独特转换方法。该方法生成逼真且语义有效的轨迹变体，无需标记监督即可学习可泛化的前缀表示。在真实事件日志上的实验表明，与现有的最先进基线相比，SiamSA-PPM在预测下一个活动和最终结果方面均取得了具有竞争力或更优的性能。 AI

影响这项研究有望提高标记数据稀缺行业中预测性过程监控的准确性。

排序理由该集群描述了一篇详细介绍新研究方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍新研究方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 5 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Sjoerd van Straten, Alessandro Padella, Marwan Hassani · 2026-10-21 04:00

面向标记数据稀疏场景下的过程预测的感知过程事件日志增强

arXiv:2610.24777v2 Announce Type: replace Abstract: Predictive Process Monitoring (PPM) forecasts future events of ongoing business processes based on event logs. However, deep learning PPM approaches are often limited by labeled data scarcity and the low variability of real-worl…

本文如何被排名

报道来源 [1]

面向标记数据稀疏场景下的过程预测的感知过程事件日志增强

相关实体

相关话题