Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples
This work addresses the need for interpretability in KGE models, which is important for users in fields like semantic web and AI, but it is incremental as it builds on existing explanation techniques.
The paper tackles the problem of explaining link predictions in Knowledge Graph Embedding models by proposing an example-based approach that uses latent space representations, and it shows that this method outperforms baselines on two public datasets.
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.