High-Dimensional Similarity Search with Quantum-Assisted Variational Autoencoder

TL;DR

This paper demonstrates the application of a quantum-assisted variational autoencoder for high-dimensional similarity search, showing promising results in speed and memory efficiency on large datasets.

Contribution

It extends previous work by applying QVAE to real-world high-dimensional data, constructing a space-efficient index, and demonstrating scalability and speedups.

Findings

Correlation between Hamming and Euclidean distances in embedded space

Speedup over linear search methods

Scalability to half a billion data points

Abstract

Recent progress in quantum algorithms and hardware indicates the potential importance of quantum computing in the near future. However, finding suitable application areas remains an active area of research. Quantum machine learning is touted as a potential approach to demonstrate quantum advantage within both the gate-model and the adiabatic schemes. For instance, the Quantum-assisted Variational Autoencoder has been proposed as a quantum enhancement to the discrete VAE. We extend on previous work and study the real-world applicability of a QVAE by presenting a proof-of-concept for similarity search in large-scale high-dimensional datasets. While exact and fast similarity search algorithms are available for low dimensional datasets, scaling to high-dimensional data is non-trivial. We show how to construct a space-efficient search index based on the latent space representation of a QVAE. Our experiments show a correlation between the Hamming distance in the embedded space and the Euclidean distance in the original space on the Moderate Resolution Imaging Spectroradiometer (MODIS) dataset. Further, we find real-world speedups compared to linear search and demonstrate memory-efficient scaling to half a billion data points.