Combining Abstract Argumentation and Machine Learning for Efficiently Analyzing Low-Level Process Event Streams

2025-05-09

AI Summary

Process-oriented event stream interpretation—accurately mapping low-level events to business activity steps under scarce annotations and highly ambiguous event-to-activity mappings—remains challenging. Method: This paper proposes a data- and computation-efficient neuro-symbolic approach that jointly leverages a context-aware sequence labeling model and an Abstract Argumentation Framework (AAF). The neural component generates candidate activity interpretations, while the symbolic AAF refines them using domain-specific prior knowledge, enabling interpretable, small-sample reasoning via neuro-symbolic co-inference. Contribution/Results: Compared to purely data-driven methods, our approach substantially reduces reliance on manual annotation and computational resources, thereby lowering carbon footprint. Empirical evaluation demonstrates high accuracy and strong interpretability in process intelligence tasks, validating the feasibility of green AI for business process analysis.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Data Mining & Knowledge Management: Intelligent Query Processing
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Monitoring and analyzing process traces is a critical task for modern companies and organizations. In scenarios where there is a gap between trace events and reference business activities, this entails an interpretation problem, amounting to translating each event of any ongoing trace into the corresponding step of the activity instance. Building on a recent approach that frames the interpretation problem as an acceptance problem within an Abstract Argumentation Framework (AAF), one can elegantly analyze plausible event interpretations (possibly in an aggregated form), as well as offer explanations for those that conflict with prior process knowledge. Since, in settings where event-to-activity mapping is highly uncertain (or simply under-specified) this reasoning-based approach may yield lowly-informative results and heavy computation, one can think of discovering a sequencetagging model, trained to suggest highly-probable candidate event interpretations in a context-aware way. However, training such a model optimally may require using a large amount of manually-annotated example traces. Considering the urgent need of developing Green AI solutions enabling environmental and societal sustainability (with reduced labor/computational costs and carbon footprint), we propose a data/computation-efficient neuro-symbolic approach to the problem, where the candidate interpretations returned by the example-driven sequence tagger is refined by the AAF-based reasoner. This allows us to also leverage prior knowledge to compensate for the scarcity of example data, as confirmed by experimental results; clearly, this property is particularly useful in settings where data annotation and model optimization costs are subject to stringent constraints.

Problem

• Bridging gap between trace events and business activities interpretation
• Reducing computational costs in uncertain event-to-activity mapping scenarios
• Combining machine learning and argumentation for efficient process analysis

Innovation

• Combines Abstract Argumentation with Machine Learning
• Uses sequence-tagging for context-aware interpretations
• Neuro-symbolic approach reduces data and computation needs