Quantum Feature Optimization for Enhanced Clustering of Blockchain Transaction Data

TL;DR

This paper explores quantum-enhanced feature extraction methods to improve clustering of complex blockchain transaction data, showing that shallow quantum circuits can significantly enhance clustering accuracy.

Contribution

It introduces a novel hybrid and fully quantum clustering framework using quantum neural networks for feature optimization in high-dimensional data.

Findings

Quantum feature extraction improves clustering performance.

Shallow quantum circuits can effectively learn meaningful representations.

Quantum approaches outperform classical clustering in noisy, high-dimensional data.

Abstract

Blockchain transaction data exhibits high dimensionality, noise, and intricate feature entanglement, presenting significant challenges for traditional clustering algorithms. In this study, we conduct a comparative analysis of three clustering approaches: (1) Classical K-Means Clustering, applied to pre-processed feature representations; (2) Hybrid Clustering, wherein classical features are enhanced with quantum random features extracted using randomly initialized quantum neural networks (QNNs); and (3) Fully Quantum Clustering, where a QNN is trained in a self-supervised manner leveraging a SwAV-based loss function to optimize the feature space for clustering directly. The proposed experimental framework systematically investigates the impact of quantum circuit depth and the number of learned prototypes, demonstrating that even shallow quantum circuits can effectively extract meaningful non-linear representations, significantly improving clustering performance.