Quantum-Enhanced K-Nearest Neighbors for Text Classification: A Hybrid Approach with Unified Circuit and Reduced Quantum Gates

Abstract

Text classification, a key process in natural language processing (NLP), relies on the k-nearest neighbors (KNN) algorithm for its simplicity and effectiveness. Traditional methods often grapple with the high-dimensional nature of textual data, leading to substantial computational demands. This study introduces a novel classical quantum k-nearest neighbors (CQKNN) algorithm, which integrates quantum circuits into a conventional machine-learning framework to enhance computational efficiency and reduce storage requirements. This hybrid approach uses a unified quantum circuit that simplifies multiple similarity calculations through mid-circuit measurements and qubit reset operations, significantly improving upon traditional multi-circuit quantum k-nearest neighbors (QKNN) models. The CQKNN algorithm, tested on datasets such as SMS Spam Collection, Twitter US Airline Sentiment, and IMDB Movie Reviews, not only outperforms classical KNN but also addresses challenges posed by noisy intermediate-scale quantum (NISQ) devices through advanced error mitigation techniques. This work highlights resource efficiency and reduced gate complexity and demonstrates the practical application of fidelity in quantum similarity calculations, setting new standards for quantum-enhanced machine learning and advancing current quantum technology capabilities in complex data classification tasks.