Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion

12/04/2019
by   Koki Kishimoto, et al.
0

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.

READ FULL TEXT
research
02/08/2019

Binarized Knowledge Graph Embeddings

Tensor factorization has become an increasingly popular approach to know...
research
03/27/2019

Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction Perspective

Knowledge graph is a popular format for representing knowledge, with man...
research
10/02/2020

Knowledge Graph Embeddings in Geometric Algebras

Knowledge graph (KG) embedding aims at embedding entities and relations ...
research
12/07/2018

Improved Knowledge Graph Embedding using Background Taxonomic Information

Knowledge graphs are used to represent relational information in terms o...
research
05/13/2022

Kronecker Decomposition for Knowledge Graph Embeddings

Knowledge graph embedding research has mainly focused on learning contin...
research
06/08/2022

ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion

Knowledge graphs are inherently incomplete. Therefore substantial resear...
research
03/25/2018

Bernoulli Embeddings for Graphs

Just as semantic hashing can accelerate information retrieval, binary va...

Please sign up or login with your details

Forgot password? Click here to reset