Search

Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex and opaque machine learning (ML) models. Despite the development of a multitude of methods to explain the decisions of black-box classifiers in recent years, these tools are seldomly used beyond visualization purposes. Only recently, researchers have started to employ explanations in practice to actually improve models. This paper offers a comprehensive overview over techniques that apply XAI practically to obtain better ML models, and systematically categorizes these approaches, comparing their respective strengths and weaknesses. We provide a theoretical perspective on these methods, and show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning, among others. We further discuss potential caveats and drawbacks of these methods. We conclude that while model improvement based on XAI can have significant beneficial effects even on complex and not easily quantifiable model properties, these methods need to be applied carefully, since their success can vary depending on a number of factors, such as the model and dataset used, or the employed explanation method. [Display omitted] • We show how and why XAI improves several model properties in toy experiments. • We develop a unifying theoretical framework for XAI-based model improvement. • We extensively review and discuss existing approaches that use XAI to improve models. • We provide experiment-supported practical recommendations for XAI-based augmentation. [ABSTRACT FROM AUTHOR]

Robustness has become an important consideration in deep learning. With the help of explainable AI, mismatches between an explained model's decision strategy and the user's domain knowledge (e.g. Clever Hans effects) have been identified as a starting point for improving faulty models. However, it is less clear what to do when the user and the explanation agree. In this paper, we demonstrate that acceptance of explanations by the user is not a guarantee for a machine learning model to be robust against Clever Hans effects, which may remain undetected. Such hidden flaws of the model can nevertheless be mitigated, and we demonstrate this by contributing a new method, Explanation-Guided Exposure Minimization (EGEM), that preemptively prunes variations in the ML model that have not been the subject of positive explanation feedback. Experiments demonstrate that our approach leads to models that strongly reduce their reliance on hidden Clever Hans strategies, and consequently achieve higher accuracy on new data. • Explainable AI may not detect all Clever Hans effects in practical ML scenarios. • Hidden Clever Hans effects can be mitigated using Exposure Minimization. • We propose a solution in the form of a soft-pruning scheme on network activations. • We demonstrate the practical benefits of our approach on image and text data. [ABSTRACT FROM AUTHOR]