Fast Knowledge Graph Completion using Graphics Processing Units

TL;DR

This paper introduces a GPU-accelerated framework for knowledge graph completion that transforms the problem into a similarity join task, enabling faster processing of large-scale knowledge graphs.

Contribution

It proposes a novel GPU-based method that transforms knowledge graph completion into a similarity join problem for models in a metric space, improving efficiency.

Findings

Significantly faster completion times on large knowledge graphs

Effective transformation of completion problem into similarity join

Demonstrated scalability and efficiency of the GPU framework

Abstract

Knowledge graphs can be used in many areas related to data semantics such as question-answering systems, knowledge based systems. However, the currently constructed knowledge graphs need to be complemented for better knowledge in terms of relations. It is called knowledge graph completion. To add new relations to the existing knowledge graph by using knowledge graph embedding models, we have to evaluate $N\times N \times R$ vector operations, where $N$ is the number of entities and $R$ is the number of relation types. It is very costly. In this paper, we provide an efficient knowledge graph completion framework on GPUs to get new relations using knowledge graph embedding vectors. In the proposed framework, we first define "transformable to a metric space" and then provide a method to transform the knowledge graph completion problem into the similarity join problem for a model which is "transformable to a metric space". After that, to efficiently process the similarity join problem, we derive formulas using the properties of a metric space. Based on the formulas, we develop a fast knowledge graph completion algorithm. Finally, we experimentally show that our framework can efficiently process the knowledge graph completion problem.