When to choose ranked area integrals versus integrated gradient for explainable artificial intelligence – a comparison of algorithms

Abstract

PurposeExplainable artificial intelligence (XAI) has importance in several industrial applications. The study aims to provide a comparison of two important methods used for explainable AI algorithms.Design/methodology/approachIn this study multiple criteria has been used to compare between explainable Ranked Area Integrals (xRAI) and integrated gradient (IG) methods for the explainability of AI algorithms, based on a multimethod phase-wise analysis research design.FindingsThe theoretical part includes the comparison of frameworks of two methods. In contrast, the methods have been compared across five dimensions like functional, operational, usability, safety and validation, from a practical point of view.Research limitations/implicationsA comparison has been made by combining criteria from theoretical and practical points of view, which demonstrates tradeoffs in terms of choices for the user.Originality/valueOur results show that the xRAI method performs better from a theoretical point of view. However, the IG method shows a good result with both model accuracy and prediction quality.

Explainable AI for unveiling deep learning pollen classification model based on fusion of scattered light patterns and fluorescence spectroscopy

“…Term attributions is common in model interpretability and multiple attribution algorithms are associated with it. Algorithms can rely on different principles to quantify attributions such as gradients 23,46,47 or perturbations [48][49][50] . For our study we selected integrated gradient attribution method 23 that uses the input's gradients after back-propagation and does not require modification of the original network.…”

Explainable AI for unveiling deep learning pollen classification model based on fusion of scattered light patterns and fluorescence spectroscopy

“…Term attributions is common in model interpretability and multiple attribution algorithms are associated with it. Algorithms can rely on different principles to quantify attributions such as gradients 33,35,36 or perturbations [37][38][39] . For our study we selected integrated gradient attribution method 33 that uses the input's gradients after back-propagation and does not require modification of the original network.…”