Effects of Locality and Rule Language on Explanations for Knowledge Graph Embeddings

by   Luis Galárraga, et al.

Knowledge graphs (KGs) are key tools in many AI-related tasks such as reasoning or question answering. This has, in turn, propelled research in link prediction in KGs, the task of predicting missing relationships from the available knowledge. Solutions based on KG embeddings have shown promising results in this matter. On the downside, these approaches are usually unable to explain their predictions. While some works have proposed to compute post-hoc rule explanations for embedding-based link predictors, these efforts have mostly resorted to rules with unbounded atoms, e.g., bornIn(x,y) => residence(x,y), learned on a global scope, i.e., the entire KG. None of these works has considered the impact of rules with bounded atoms such as nationality(x,England) => speaks(x, English), or the impact of learning from regions of the KG, i.e., local scopes. We therefore study the effects of these factors on the quality of rule-based explanations for embedding-based link predictors. Our results suggest that more specific rules and local scopes can improve the accuracy of the explanations. Moreover, these rules can provide further insights about the inner-workings of KG embeddings for link prediction.


page 1

page 2

page 3

page 4


Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning

Reasoning is essential for the development of large knowledge graphs, es...

Towards Loosely-Coupling Knowledge Graph Embeddings and Ontology-based Reasoning

Knowledge graph completion (a.k.a. link prediction), i.e., the task of i...

SAFRAN: An interpretable, rule-based link prediction method outperforming embedding models

Neural embedding-based machine learning models have shown promise for pr...

Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs

Neural embedding-based machine learning models have shown promise for pr...

Combination of Unified Embedding Model and Observed Features for Knowledge Graph Completion

Knowledge graphs are useful for many artificial intelligence tasks but o...

Beyond Markov Logic: Efficient Mining of Prediction Rules in Large Graphs

Graph representations of large knowledge bases may comprise billions of ...

Initial Foundation for Predicting Individual Earthquake's Location and Magnitude by Using Glass-Box Physics Rule Learner

Although researchers accumulated knowledge about seismogenesis and decad...

Please sign up or login with your details

Forgot password? Click here to reset