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

by   Dmitry Kazhdan, et al.

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 functional groups to explain GNNs trained on molecular property prediction tasks, and implement interpretations with a 0.76 AUCROC completeness score.


page 5

page 6

page 7

page 8

page 16

page 17

page 18

page 19


Encoding Concepts in Graph Neural Networks

The opaque reasoning of Graph Neural Networks induces a lack of human tr...

Understanding Graph and Understanding Map and their Potential Applications

Based on the previously proposed concept Understanding Tree, this paper ...

Physical Pooling Functions in Graph Neural Networks for Molecular Property Prediction

Graph neural networks (GNNs) are emerging in chemical engineering for th...

ProGReST: Prototypical Graph Regression Soft Trees for Molecular Property Prediction

In this work, we propose the novel Prototypical Graph Regression Self-ex...

Graph Neural Network Architecture Search for Molecular Property Prediction

Predicting the properties of a molecule from its structure is a challeng...

Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis

Graph neural networks (GNNs) are highly effective on a variety of graph-...

Please sign up or login with your details

Forgot password? Click here to reset