Toward Explainable AI for Regression Models
It tackles the problem of interpretability in regression models for safety-critical and medical applications, but is incremental as it builds on existing XAI work.
The paper addresses the lack of attention to explainable AI for regression models, clarifying conceptual differences from classification and providing theoretical insights and practical demonstrations.
In addition to the impressive predictive power of machine learning (ML) models, more recently, explanation methods have emerged that enable an interpretation of complex non-linear learning models such as deep neural networks. Gaining a better understanding is especially important e.g. for safety-critical ML applications or medical diagnostics etc. While such Explainable AI (XAI) techniques have reached significant popularity for classifiers, so far little attention has been devoted to XAI for regression models (XAIR). In this review, we clarify the fundamental conceptual differences of XAI for regression and classification tasks, establish novel theoretical insights and analysis for XAIR, provide demonstrations of XAIR on genuine practical regression problems, and finally discuss the challenges remaining for the field.