Biclustering a dataset using photonic quantum computing

TL;DR

This paper explores how quantum photonic computing models like boson and Gaussian boson sampling can be applied to biclustering in datasets, proposing heuristics that leverage quantum sampling to identify dense subgraphs.

Contribution

It introduces a novel approach using quantum photonic sampling methods for biclustering, connecting quantum computing models to data mining tasks.

Findings

Simulations show promising results for quantum-based biclustering heuristics.

Proposed methods effectively identify dense subgraphs in bipartite graphs.

Highlights potential for quantum computing to enhance data clustering techniques.

Abstract

Biclustering is a problem in machine learning and data mining that seeks to group together rows and columns of a dataset according to certain criteria. In this work, we highlight the natural relation that quantum computing models like boson and Gaussian boson sampling (GBS) have to this problem. We first explore the use of boson sampling to identify biclusters based on matrix permanents. We then propose a heuristic that finds clusters in a dataset using Gaussian boson sampling by (i) converting the dataset into a bipartite graph and then (ii) running GBS to find the densest sub-graph(s) within the larger bipartite graph. Our simulations for the above proposed heuristics show promising results for future exploration in this area.