aiqbench analysis
This paper introduces RAW-Explainer, a novel method for generating interpretable subgraph explanations specifically tailored to path reasoning graph neural networks used in knowledge graph completion. By leveraging random walk objectives and heterogeneous information, the approach effectively addresses distribution shifts between full graphs and smaller explanatory subgraphs while maintaining computational efficiency. The work advances the field of machine learning explainability by providing factual, connected insights into how these models make link prediction decisions.
RAW-Explainer: Post-hoc Explanations of Path Reasoning Graph Neural Networks for Knowledge Graph Completion
arXiv:2506.12558v2 Announce Type: replace Abstract: Path reasoning graph neural networks have demonstrated state-of-the-art performance on knowledge graph completion tasks such as link prediction. However, interpreting their predictions remains a challenging open problem, as most GNN explainability methods target node-level or graph-level tasks. In this paper, we propose RAW-Explainer ($\underline{Ra}$ndom $\underline{W}$alk Explainer), a novel explainability method tailored to path reasoning GNNs that generates connected, concise, and interpretable subgraph explanations for link prediction in knowledge graphs. Our method uses heterogeneous information to identify factual explanations and encourages connectivity through a random walk objective, using a parameterized model for efficient collective explanation. Furthermore, RAW-Explainer overcomes the distribution shift issue when evaluating explanatory subgraphs that are orders of magnitude smaller than the full graph by proposing a robust evaluator that generalizes to the subgraph distribution. Extensive results on standard knowledge graph completion benchmarks demonstrate that our approach strikes a balance between explanation quality and computational efficiency. Code and data are available at: https://github.com/colab-nyuad/RAWExplainer
Abstract:Path reasoning graph neural networks have demonstrated state-of-the-art performance on knowledge graph completion tasks such as link prediction. However, interpreting their predictions remains a challenging open problem, as most GNN explainability methods target node-level or graph-level tasks. In this paper, we propose RAW-Explainer ($\underline{Ra}$ndom $\underline{W}$alk Explainer), a novel explainability method tailored to path reasoning GNNs that generates connected, concise, and interpretable subgraph explanations for link prediction in knowledge graphs. Our method uses heterogeneous information to identify factual explanations and encourages connectivity through a random walk objective, using a parameterized model for efficient collective explanation. Furthermore, RAW-Explainer overcomes the distribution shift issue when evaluating explanatory subgraphs that are orders of magnitude smaller than the full graph by proposing a robust evaluator that generalizes to the subgraph distribution. Extensive results on standard knowledge graph completion benchmarks demonstrate that our approach strikes a balance between explanation quality and computational efficiency. Code and data are available at: this https URL
Machine Learning (cs.LG); Machine Learning (stat.ML)
arXiv:2506.12558 [cs.LG]
(or arXiv:2506.12558v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2506.12558 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 251 words
