Variational Quantum Circuit Model for Knowledge Graphs Embedding

TL;DR

This paper introduces two novel variational quantum circuit models for knowledge graph embedding, demonstrating comparable performance to classical models and potential efficiency improvements in inference.

Contribution

It presents the first quantum ansatzes for knowledge graph embedding, with one model maintaining quantum advantages during training.

Findings

Achieved results comparable to classical models like RESCAL and DistMult.

Proposed models can potentially reduce inference complexity on knowledge graphs.

Efficient training of quantum embeddings while preserving quantum benefits.

Abstract

In this work, we propose the first quantum Ans\"atze for the statistical relational learning on knowledge graphs using parametric quantum circuits. We introduce two types of variational quantum circuits for knowledge graph embedding. Inspired by the classical representation learning, we first consider latent features for entities as coefficients of quantum states, while predicates are characterized by parametric gates acting on the quantum states. For the first model, the quantum advantages disappear when it comes to the optimization of this model. Therefore, we introduce a second quantum circuit model where embeddings of entities are generated from parameterized quantum gates acting on the pure quantum state. The benefit of the second method is that the quantum embeddings can be trained efficiently meanwhile preserving the quantum advantages. We show the proposed methods can achieve comparable results to the state-of-the-art classical models, e.g., RESCAL, DistMult. Furthermore, after optimizing the models, the complexity of inductive inference on the knowledge graphs might be reduced with respect to the number of entities.