Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis

2024/11/28 by Atzmueller, Martin, Bohne, Tim, Windler, Patricia
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2412.00146

Abstract

Knowledge-augmented learning enables the combination of knowledge-based and data-driven approaches. For anomaly detection and diagnosis, understandability is typically an important factor, especially in high-risk areas. Therefore, explainability and interpretability are also major criteria in such contexts. This chapter focuses on knowledge-augmented explainable and interpretable learning to enhance understandability, transparency and ultimately computational sensemaking. We exemplify different approaches and methods in the domains of anomaly detection and diagnosis - from comparatively simple interpretable methods towards more advanced neuro-symbolic approaches.

Related

• A general-purpose method for applying Explainable AI for Anomaly Detection
• Explainable AI: A Review of Machine Learning Interpretability Methods
• A Survey on Explainable Anomaly Detection
• ECATS: Explainable-by-design concept-based anomaly detection for time series
• Transparent Anomaly Detection via Concept-based Explanations