Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples
Not on the map. Why?
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 9 of its 15 references that are in the map. First posted on arXiv 5 Dec 2022.
Builds on
9 of 15 references.
References · 9
- 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
- 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
- 2020CoDEx: A Comprehensive Knowledge Graph Completion Benchmarkcited by 102
- 2019Investigating Robustness and Interpretability of Link Prediction via Adversarial Modificationscited by 25
- 2019Probability Calibration for Knowledge Graph Embedding Modelscited by 20
- 2020Knowledge Graph Embeddings and Explainable AIcited by 15
- 2021Poisoning Knowledge Graph Embeddings via Relation Inference Patternscited by 12
- 2019ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictionscited by 10
- 2020Explaining Neural Matrix Factorization with Gradient Rollbackcited by 5
Built on by
Citing papers per year: 2024: 2.
2 papers.