Algorithmic Concept-based Explainable Reasoning

by   Dobrik Georgiev, et al.

Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems. This has numerous benefits, such as allowing applications of algorithms when preconditions are not satisfied, or reusing learned models when sufficient training data is not available or can't be generated. Unfortunately, a key hindrance of these approaches is their lack of explainability, since GNNs are black-box models that cannot be interpreted directly. In this work, we address this limitation by applying existing work on concept-based explanations to GNN models. We introduce concept-bottleneck GNNs, which rely on a modification to the GNN readout mechanism. Using three case studies we demonstrate that: (i) our proposed model is capable of accurately learning concepts and extracting propositional formulas based on the learned concepts for each target class; (ii) our concept-based GNN models achieve comparative performance with state-of-the-art models; (iii) we can derive global graph concepts, without explicitly providing any supervision on graph-level concepts.



There are no comments yet.


page 1

page 2

page 3

page 4


Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks

Graph Neural Networks (GNNs) are deep learning models that take graph da...

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...

Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense

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

RelEx: A Model-Agnostic Relational Model Explainer

In recent years, considerable progress has been made on improving the in...

A Novel Higher-order Weisfeiler-Lehman Graph Convolution

Current GNN architectures use a vertex neighborhood aggregation scheme, ...

Concept Bottleneck Models

We seek to learn models that we can interact with using high-level conce...

Toward a Unified Framework for Debugging Gray-box Models

We are concerned with debugging concept-based gray-box models (GBMs). Th...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.