Fast variational knowledge graph embedding

TL;DR

This paper introduces a quantum-enhanced method for knowledge graph embedding that leverages superposition to significantly reduce training time, enabling more efficient processing of large-scale knowledge graphs.

Contribution

It presents a novel quantum approach that trains multiple knowledge graph elements simultaneously, achieving additional quantum speedup over existing variational quantum algorithms.

Findings

Quantum superposition reduces training time for KG embedding

Method scales efficiently with large knowledge graphs

Demonstrates potential for quantum advantage in KG tasks

Abstract

Embedding of a knowledge graph(KG) entities and relations in the form of vectors is an important aspect for the manipulation of the KG database for several downstream tasks, such as link prediction, knowledge graph completion, and recommendation. Because of the growing size of the knowledge graph databases, it has become a daunting task for the classical computer to train a model efficiently. Quantum computer can help speedup the embedding process of the KGs by encoding the entities into a variational quantum circuit of polynomial depth. Usually, the time complexity for such variational circuit-dependent quantum classical algorithms for each epoch is $\mathcal{O}(N \mbox{poly}(\log M))$, where $N$ is number of elements in the knowledge graph and $M$ is the number of features of each entities of the knowledge graph. In this article we exploit additional quantum advantage by training multiple elements of KG in superpositions, thereby reducing the computing time further for the knowledge graph embedding model.