GCI: A (G)raph (C)oncept (I)nterpretation Framework

Dmitry Kazhdan, Botty Dimanov, Lucie Charlotte Magister, Pietro Barbiero, Mateja Jamnik, Pietro Lio

Keywords: Graph Neural Networks, Concept Extraction, Molecular Property Prediction, Interpretation

TL;DR: We propose a new framework for quantitatively evaluating concepts extracted from Graph Neural Networks, and show applications to molecular property prediction.

Abstract: Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks. An important challenge facing concept extraction approaches is the difficulty of interpreting and evaluating discovered concepts, especially for complex tasks such as molecular property prediction. We address this challenge by presenting GCI: a (G)raph (C)oncept (I)nterpretation framework, used for quantitatively measuring alignment between concepts discovered from Graph Neural Networks (GNNs) and their corresponding human interpretations. GCI encodes concept interpretations as functions, which can be used to quantitatively measure the alignment between a given interpretation and concept definition. We demonstrate four applications of GCI: (i) quantitatively evaluating concept extractors, (ii) measuring alignment between concept extractors and human interpretations, (iii) measuring the completeness of interpretations with respect to an end task and (iv) a practical application of GCI to molecular property prediction, in which we demonstrate how to use chemical \textit{functional groups} to explain GNNs trained on molecular property prediction tasks, and implement interpretations with a $0.76$ AUCROC completeness score.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2302.04899/code)