Holographic Embeddings of Knowledge Graphs

Authors

  • Maximilian Nickel Massachusetts Institute of Technology and Istituto Italiano di Tecnologia
  • Lorenzo Rosasco Universita Degli Studi di Genova, Istituto Italiano di Tecnologia, and Massachusetts Institute of Technology
  • Tomaso Poggio Massachusetts Institute of Technology

DOI:

https://doi.org/10.1609/aaai.v30i1.10314

Keywords:

Knowledge Graph, Compositional Embeddings, Holographic Embeddings

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. Experimentally, we show that holographic embeddings are able to outperform state-of-the-art methods for link prediction on knowledge graphs and relational learning benchmark datasets.

Downloads

Published

2016-03-02

How to Cite

Nickel, M., Rosasco, L., & Poggio, T. (2016). Holographic Embeddings of Knowledge Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). https://doi.org/10.1609/aaai.v30i1.10314

Issue

Section

Technical Papers: Machine Learning Methods