# Utilizing Description Logics for Global Explanations of Heterogeneous Graph Neural Networks

arXiv: https://arxiv.org/abs/2405.12654 · HTML: https://mlsanity.com/paper/2405.12654/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 21 May 2024.

## Builds on (most cited first, 21 of 21)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [Generative Causal Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.06643/) (2021)
- [Generalizing Graph Neural Networks on Out-Of-Distribution Graphs](https://mlsanity.com/paper/2111.10657/) (2021)
- [Global Explainability of GNNs via Logic Combination of Learned Concepts](https://mlsanity.com/paper/2210.07147/) (2022)
- [Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability](https://mlsanity.com/paper/2207.09615/) (2022)
- [A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics](https://mlsanity.com/paper/2207.12599/) (2022)
- [Graph Neural Networks Designed for Different Graph Types: A Survey](https://mlsanity.com/paper/2204.03080/) (2022)
- [EvoLearner: Learning Description Logics with Evolutionary Algorithms](https://mlsanity.com/paper/2111.04879/) (2021)
- [Learning Concept Lengths Accelerates Concept Learning in ALC](https://mlsanity.com/paper/2107.04911/) (2021)
- [Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding](https://mlsanity.com/paper/2209.11414/) (2022)
- [GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifs](https://mlsanity.com/paper/2202.08815/) (2022)
- [Combining Sub-Symbolic and Symbolic Methods for Explainability](https://mlsanity.com/paper/2112.01844/) (2021)

## Built on by (most cited first, 4 of 4)

- [Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective](https://mlsanity.com/paper/2502.02719/) (2025)
- [Sound Logical Explanations for Mean Aggregation Graph Neural Networks](https://mlsanity.com/paper/2511.11593/) (2025)
- [WILTing Trees: Interpreting the Distance Between MPNN Embeddings](https://mlsanity.com/paper/2505.24642/) (2025)
- [Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark](https://mlsanity.com/paper/2610.03526/) (2026)

## Abstract (arXiv)

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.