arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.26461cs.LGcs.AIcs.SC
收藏

神经符号过程异常检测

Neuro-Symbolic Process Anomaly Detection

RWTH Aachen University（亚琛工业大学）；Eindhoven University of Technology（埃因霍温理工大学）

Devashish Gaikwad, Wil M. P. van der Aalst, Gyunam Park

备注：
Accepted at CAiSE2026
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种神经符号方法，利用逻辑张量网络和Declare约束，将领域知识整合到神经异常检测中，提升F1分数，尤其在少量符合轨迹时表现更优。

摘要：

过程异常检测是过程挖掘中识别过程正常行为偏离的重要应用。基于神经网络的方法最近被应用于此任务，直接从事件日志学习而无需预定义的过程模型。然而，由于异常检测是纯粹的统计任务，这些模型无法整合人类领域知识。因此，罕见但符合的轨迹常被误判为异常，限制了检测效果。神经符号AI领域的最新发展引入了逻辑张量网络（LTN）作为整合符号知识到神经网络的手段。本文提出一种神经符号方法，利用LTN和Declare约束将领域知识整合到神经异常检测中。使用自编码器模型为基础，将Declare约束编码为学习过程中的软逻辑指导规则，以区分异常和罕见但符合的行为。在合成和真实数据集上的评估表明，即使在仅有10个符合轨迹时，本文方法也能提高F1分数，且Declare约束的选择直接影响性能提升。

英文摘要：

Process anomaly detection is an important application of process mining for identifying deviations from the normal behavior of a process. Neural network-based methods have recently been applied to this task, learning directly from event logs without requiring a predefined process model. However, since anomaly detection is a purely statistical task, these models fail to incorporate human domain knowledge. As a result, rare but conformant traces are often misclassified as anomalies due to their low frequency, which limits the effectiveness of the detection process. Recent developments in the field of neuro-symbolic AI have introduced Logic Tensor Networks (LTN) as a means to integrate symbolic knowledge into neural networks using real-valued logic. In this work, we propose a neuro-symbolic approach that integrates domain knowledge into neural anomaly detection using LTN and Declare constraints. Using autoencoder models as a foundation, we encode Declare constraints as soft logical guiderails within the learning process to distinguish between anomalous and rare but conformant behavior. Evaluations on synthetic and real-world datasets demonstrate that our approach improves F1 scores even when as few as 10 conformant traces exist, and that the choice of Declare constraint and by extension human domain knowledge significantly influences performance gains.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑