Knowledge-Augmented Explainable and Interpretable Learning for Anomaly Detection and Diagnosis
It addresses the need for interpretable models in high-risk domains like anomaly detection, but appears incremental as it reviews existing approaches.
The chapter explores knowledge-augmented learning to improve explainability and interpretability in anomaly detection and diagnosis, focusing on enhancing understandability and transparency through various methods.
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.