# Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples

arXiv: https://arxiv.org/abs/2212.02651 · HTML: https://mlsanity.com/paper/2212.02651/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 5 Dec 2022.

## Builds on (most cited first, 9 of 9)

- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [CoDEx: A Comprehensive Knowledge Graph Completion Benchmark](https://mlsanity.com/paper/2009.07810/) (2020)
- [Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications](https://mlsanity.com/paper/1905.00563/) (2019)
- [Probability Calibration for Knowledge Graph Embedding Models](https://mlsanity.com/paper/1912.10000/) (2019)
- [Knowledge Graph Embeddings and Explainable AI](https://mlsanity.com/paper/2004.14843/) (2020)
- [Poisoning Knowledge Graph Embeddings via Relation Inference Patterns](https://mlsanity.com/paper/2111.06345/) (2021)
- [ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictions](https://mlsanity.com/paper/1904.12694/) (2019)
- [Explaining Neural Matrix Factorization with Gradient Rollback](https://mlsanity.com/paper/2010.05516/) (2020)

## Built on by (most cited first, 2 of 2)

- [Path-based Explanation for Knowledge Graph Completion](https://mlsanity.com/paper/2401.02290/) (2024)
- [eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules](https://mlsanity.com/paper/2412.04846/) (2024)

## Abstract (arXiv)

We study the problem of explaining link predictions in the Knowledge Graph Embedding (KGE) models. We propose an example-based approach that exploits the latent space representation of nodes and edges in a knowledge graph to explain predictions. We evaluated the importance of identified triples by observing progressing degradation of model performance upon influential triples removal. Our experiments demonstrate that this approach to generate explanations outperforms baselines on KGE models for two publicly available datasets.