Towards symbolic XAI - explanation through human understandable logical relationships between features

Thomas Schnake, Farnoush Rezaei Jafari, Jonas Lederer, Ping Xiong, Shinichi Nakajima, Stefan Gugler, Grégoire Montavon, Klaus-Robert Müller

Abstract: Highlights•While classical XAI techniques are useful, more structured explanations are required•We propose a new post-hoc XAI framework for explaining ML models in a symbolic manner•Our framework is interoperable with XAI techniques such as Shapley values and LRP•Symbolic XAI explains ML models faithfully for image, text, and chemistry data