Binarized Canonical Polyadic Decomposition for Knowledge Graph Completion

Abstract

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.

arXiv commentarXiv admin note: substantial text overlap with arXiv:1902.02970

References in corpus (8)

• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• A Review of Relational Machine Learning for Knowledge Graphs
• A Survey on Methods and Theories of Quantized Neural Networks
• On Multi-Relational Link Prediction with Bilinear Models
• Logistic Tensor Factorization for Multi-Relational Data
• On the Equivalence of Holographic and Complex Embeddings for Link Prediction
• Word2Bits - Quantized Word Vectors
• Data-dependent Learning of Symmetric/Antisymmetric Relations for Knowledge Base Completion