Holographic embeddings of knowledge graphs
Author(s)
Nickel, Maximilian; Rosasco, Lorenzo; Poggio, Tomaso A
Download1510.04935.pdf (360.6Kb)
OPEN_ACCESS_POLICY
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
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-ofthe-Art methods for link prediction on knowledge graphs and relational learning benchmark datasets.
Date issued
2016-03Department
McGovern Institute for Brain Research at MIT. Center for Brains, Minds, and Machines; Massachusetts Institute of Technology. Laboratory for Computational and Statistical Learning; McGovern Institute for Brain Research at MITJournal
Thirtieth AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence
Citation
Nickel,Maximilian et al. "Holographic embeddings of knowledge graphs." Thirtieth AAAI Conference on Artificial Intelligence, February 12-17 2016, Phoenix, Arizona, Association for the Advancement of Artificial Intelligence, March 2016 © 2016 Association for the Advancement of Artificial Intelligence
Version: Author's final manuscript