Integrating Prior Knowledge in Post-hoc Explanations

Autor:	Jeyasothy, Adulam, Laugel, Thibault, Lesot, Marie-Jeanne, Marsala, Christophe, Detyniecki, Marcin
Rok vydání:	2022
Předmět:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	In the field of eXplainable Artificial Intelligence (XAI), post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. Integrating prior knowledge into such interpretability methods aims at improving the explanation understandability and allowing for personalised explanations adapted to each user. In this paper, we propose to define a cost function that explicitly integrates prior knowledge into the interpretability objectives: we present a general framework for the optimization problem of post-hoc interpretability methods, and show that user knowledge can thus be integrated to any method by adding a compatibility term in the cost function. We instantiate the proposed formalization in the case of counterfactual explanations and propose a new interpretability method called Knowledge Integration in Counterfactual Explanation (KICE) to optimize it. The paper performs an experimental study on several benchmark data sets to characterize the counterfactual instances generated by KICE, as compared to reference methods. Comment: preprint
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2204.11634 Zobrazit plný text záznamu View this record from Arxiv