Utilizing Description Logics for Global Explanations of Heterogeneous Graph Neural Networks

D. Köhler, S. Heindorf, ArXiv:2405.12654 (2024).

Preprint | English
Author
Köhler, Dominik; Heindorf, StefanLibreCat
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.
Publishing Year
Journal Title
arXiv:2405.12654
LibreCat-ID

Cite this

Köhler D, Heindorf S. Utilizing Description Logics for Global Explanations of Heterogeneous  Graph Neural Networks. arXiv:240512654. Published online 2024.
Köhler, D., & Heindorf, S. (2024). Utilizing Description Logics for Global Explanations of Heterogeneous  Graph Neural Networks. In arXiv:2405.12654.
@article{Köhler_Heindorf_2024, title={Utilizing Description Logics for Global Explanations of Heterogeneous  Graph Neural Networks}, journal={arXiv:2405.12654}, author={Köhler, Dominik and Heindorf, Stefan}, year={2024} }
Köhler, Dominik, and Stefan Heindorf. “Utilizing Description Logics for Global Explanations of Heterogeneous  Graph Neural Networks.” ArXiv:2405.12654, 2024.
D. Köhler and S. Heindorf, “Utilizing Description Logics for Global Explanations of Heterogeneous  Graph Neural Networks,” arXiv:2405.12654. 2024.
Köhler, Dominik, and Stefan Heindorf. “Utilizing Description Logics for Global Explanations of Heterogeneous  Graph Neural Networks.” ArXiv:2405.12654, 2024.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Sources

arXiv 2405.12654

Search this title in

Google Scholar