Utilizing Description Logics for Global Explanations of Heterogeneous Graph Neural Networks

TL;DR

This paper introduces a novel method for explaining heterogeneous Graph Neural Networks globally by using class expressions from description logic, providing more expressive explanations than traditional subgraph-based methods.

Contribution

It proposes a new approach utilizing description logic class expressions for global explanations of GNNs, including scoring functions for selecting the best explanation.

Findings

CE-based explanations outperform subgraph explanations in expressiveness.

Two scoring functions effectively identify the most representative explanations.

Method enhances interpretability of heterogeneous GNNs.

Abstract

Graph Neural Networks (GNNs) are effective for node classification in graph-structured data, but they lack explainability, especially at the global level. Current research mainly utilizes subgraphs of the input as local explanations or generates new graphs as global explanations. However, these graph-based methods are limited in their ability to explain classes with multiple sufficient explanations. To provide more expressive explanations, we propose utilizing class expressions (CEs) from the field of description logic (DL). Our approach explains heterogeneous graphs with different types of nodes using CEs in the EL description logic. To identify the best explanation among multiple candidate explanations, we employ and compare two different scoring functions: (1) For a given CE, we construct multiple graphs, have the GNN make a prediction for each graph, and aggregate the predicted scores. (2) We score the CE in terms of fidelity, i.e., we compare the predictions of the GNN to the predictions by the CE on a separate validation set. Instead of subgraph-based explanations, we offer CE-based explanations.