Neuro-Symbolic Predictive Process Monitoring

TL;DR

This paper presents a Neuro-Symbolic approach to process suffix prediction in Business Process Management, integrating domain knowledge via temporal logic into deep learning models to improve accuracy and logical consistency.

Contribution

It introduces a novel differentiable logical loss using LTLf and Gumbel-Softmax, enabling explicit domain knowledge integration into sequence prediction models.

Findings

Improves suffix prediction accuracy on real-world datasets

Enhances logical compliance of generated sequences

Effective under noisy and realistic conditions

Abstract

This paper addresses the problem of suffix prediction in Business Process Management (BPM) by proposing a Neuro-Symbolic Predictive Process Monitoring (PPM) approach that integrates data-driven learning with temporal logic-based prior knowledge. While recent approaches leverage deep learning models for suffix prediction, they often fail to satisfy even basic logical constraints due to the absence of explicit integration of domain knowledge during training. We propose a novel method to incorporate Linear Temporal Logic over finite traces (LTLf) into the training process of autoregressive sequence predictors. Our approach introduces a differentiable logical loss function, defined using a soft approximation of LTLf semantics and the Gumbel-Softmax trick, which can be combined with standard predictive losses. This ensures the model learns to generate suffixes that are both accurate and logically consistent. Experimental evaluation on three real-world datasets shows that our method improves suffix prediction accuracy and compliance with temporal constraints. We also introduce two variants of the logic loss (local and global) and demonstrate their effectiveness under noisy and realistic settings. While developed in the context of BPM, our framework is applicable to any symbolic sequence generation task and contributes toward advancing Neuro-Symbolic AI.