Holographic Embeddings of Knowledge Graphs
Author(s)
Nickel, Maximilian; Rosasco, Lorenzo; Poggio, Tomaso![Thumbnail](/bitstream/handle/1721.1/100203/CBMM-Memo-039.pdf.jpg?sequence=5&isAllowed=y)
DownloadCBMM-Memo-039.pdf (677.8Kb)
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. 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.
Date issued
2015-11-16Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1510.04935
Series/Report no.
CBMM Memo Series;039
Keywords
Associative Memory, Knowledge Graph, Machine Learning
Collections
The following license files are associated with this item: