Encoding Concepts in Graph Neural Networks

by   Lucie Charlotte Magister, et al.
University of Cambridge
Sapienza University of Rome

The opaque reasoning of Graph Neural Networks induces a lack of human trust. Existing graph network explainers attempt to address this issue by providing post-hoc explanations, however, they fail to make the model itself more interpretable. To fill this gap, we introduce the Concept Encoder Module, the first differentiable concept-discovery approach for graph networks. The proposed approach makes graph networks explainable by design by first discovering graph concepts and then using these to solve the task. Our results demonstrate that this approach allows graph networks to: (i) attain model accuracy comparable with their equivalent vanilla versions, (ii) discover meaningful concepts that achieve high concept completeness and purity scores, (iii) provide high-quality concept-based logic explanations for their prediction, and (iv) support effective interventions at test time: these can increase human trust as well as significantly improve model performance.


page 6

page 15

page 16

page 19

page 20

page 21


GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks

While graph neural networks (GNNs) have been shown to perform well on gr...

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

Explainable AI (XAI) underwent a recent surge in research on concept ext...

Interpretable Neural-Symbolic Concept Reasoning

Deep learning methods are highly accurate, yet their opaque decision pro...

Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees

The completeness axiom renders the explanation of a post-hoc XAI method ...

MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation

Graph Neural Networks (GNNs) have received increasing attention due to t...

Entropy-based Logic Explanations of Neural Networks

Explainable artificial intelligence has rapidly emerged since lawmakers ...

A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts

Despite substantial progress in applying neural networks (NN) to a wide ...

Please sign up or login with your details

Forgot password? Click here to reset