Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion
Kishimoto, Koki, Hayashi, Katsuhiko, Akai, Genki, Shimbo, Masashi
Methods based on vector embeddings of knowledge graphs have been actively pursued as a promising approach to knowledge graph completion.However, embedding models generate storage-inefficient representations, particularly when the number of entities and relations, and the dimensionality of the real-valued embedding vectors are large. We present a binarized CANDECOMP/PARAFAC(CP) decomposition algorithm, which we refer to as B-CP, where real-valued parameters are replaced by binary values to reduce model size. Moreover, we show that a fast score computation technique can be developed with bitwise operations. We prove that B-CP is fully expressive by deriving a bound on the size of its embeddings. Experimental results on several benchmark datasets demonstrate that the proposed method successfully reduces model size by more than an order of magnitude while maintaining task performance at the same level as the real-valued CP model.
Dec-4-2019
- Country:
- South America > Brazil (0.04)
- Oceania > Australia
- Queensland > Brisbane (0.04)
- New South Wales > Sydney (0.04)
- North America
- Cuba (0.04)
- United States
- Nevada (0.04)
- Texas
- Travis County > Austin (0.04)
- Harris County > Houston (0.04)
- New York
- Richmond County > New York City (0.04)
- Queens County > New York City (0.04)
- New York County > New York City (0.04)
- Kings County > New York City (0.04)
- Bronx County > New York City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- California > San Diego County
- San Diego (0.04)
- Arizona > Maricopa County
- Phoenix (0.04)
- Canada
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.14)
- Alberta > Census Division No. 15
- Improvement District No. 9 > Banff (0.04)
- Europe
- Netherlands (0.04)
- Russia (0.04)
- Poland (0.04)
- Italy > Sardinia (0.04)
- Greece (0.04)
- Sweden > Stockholm
- Stockholm (0.04)
- Germany > North Rhine-Westphalia
- Cologne Region > Cologne (0.04)
- France > Auvergne-Rhône-Alpes
- Asia
- Africa
- Middle East > Egypt (0.04)
- Senegal > Kolda Region
- Kolda (0.04)
- Genre:
- Research Report > New Finding (0.46)
- Technology: