Holographic Embeddings of Knowledge Graphs

TL;DR

This paper introduces holographic embeddings (HolE), a novel method for learning scalable, efficient, and expressive vector representations of knowledge graphs that outperform existing models in link prediction tasks.

Contribution

HolE employs circular correlation for compositional embeddings, combining rich interaction modeling with computational efficiency and scalability for large knowledge graphs.

Findings

HolE outperforms state-of-the-art methods in link prediction.

HolE is efficient to compute and train.

HolE scales well to large datasets.

Abstract

Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn compositional vector space representations of entire knowledge graphs. The proposed method is related to holographic models of associative memory in that it employs circular correlation to create compositional representations. By using correlation as the compositional operator HolE can capture rich interactions but simultaneously remains efficient to compute, easy to train, and scalable to very large datasets. In extensive experiments we show that holographic embeddings are able to outperform state-of-the-art methods for link prediction in knowledge graphs and relational learning benchmark datasets.