English(EN) On the Potential of Multi-Task Learning in Predictive Process Monitoring

多任务学习在预测性流程监控方面展现出潜力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

一项新研究探讨了多任务学习（MTL）在预测性流程监控（PPM）中的潜力，PPM 是一个预测组织流程展开的领域。尽管深度学习已推动了 PPM 的发展，但大多数现有方法都使用单任务学习（STL），效率低下且错失了潜在的协同效应。本研究提出了首个针对 PPM 的 MTL 全面实证研究，评估了各种任务组合、神经架构和优化方法。研究结果表明，MTL 在下一活动预测方面提供了实质性改进，并能有效缓解类别不平衡问题，其中任务平衡对于低容量模型尤为关键。 AI

影响这项研究通过利用多任务学习，有望带来更高效、更准确的预测性流程监控系统。

排序理由该集群包含一篇详细介绍现有领域新方法的论文。[lever_c_demoted from research: ic=1 ai=0.7]

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: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍现有领域新方法的论文。[lever_c_demoted from research: ic=1 ai=0.7]
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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Lukas Kirchdorfer, Keyvan Amiri Elyasi, Heiner Stuckenschmidt · 2026-09-15 04:00

预测性流程监控中多任务学习的潜力

arXiv:2609.13477v1 Announce Type: new Abstract: Predictive Process Monitoring (PPM) forecasts how ongoing organizational processes unfold, enabling information systems to move beyond execution support toward proactive analysis and monitoring. Although deep learning has improved p…

本文如何被排名

报道来源 [1]

预测性流程监控中多任务学习的潜力

相关实体

相关话题