Knowledge Hypergraphs: Prediction Beyond Binary Relations

Bahare Fatemi, Perouz Taslakian, David Vazquez, David Poole

Abstract:

A Knowledge Hypergraph is a knowledge base where relations are defined on two or more entities. In this work, we introduce two embedding-based models that perform link prediction in knowledge hypergraphs:
(1) HSimplE is a shift-based method that is inspired by an existing model operating on knowledge graphs, in which the representation of an entity is a function of its position in the relation, and (2) HypE is a convolution-based method which disentangles the representation of an entity from its position in the relation. We test our models on two new knowledge hypergraph datasets that we obtain from Freebase, and show that both HSimplE and HypE are more effective in predicting links in knowledge hypergraphs than the proposed baselines and existing methods.
Our experiments show that HypE outperforms HSimplE when trained with fewer parameters and when tested on samples that contain at least one entity in a position never encountered during training.

Code: https://anonymous.4open.science/r/4ca032e1-cfdc-4b0f-8dca-ba0ee6afc65f/

Keywords: knowledge graphs, knowledge hypergraphs, knowledge hypergraph completion