DeepAI AI Chat
Log In Sign Up

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.


page 1

page 2

page 3

page 4


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

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

DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

We propose the fully explainable Decision Tree Graph Neural Network (DT+...

Global Explainability of GNNs via Logic Combination of Learned Concepts

While instance-level explanation of GNN is a well-studied problem with p...

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...

Global Counterfactual Explainer for Graph Neural Networks

Graph neural networks (GNNs) find applications in various domains such a...

RelEx: A Model-Agnostic Relational Model Explainer

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

Toward a Unified Framework for Debugging Gray-box Models

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