Quantum Semi-Random Forests for Qubit-Efficient Recommender Systems

TL;DR

This paper introduces a hybrid quantum-classical recommender system that efficiently compresses item features to operate within the limited qubit capacity of current quantum devices, achieving comparable accuracy to full-feature models.

Contribution

It presents a novel three-stage hybrid algorithm combining feature compression, quantum optimization, and a quantum semi-random forest to enable qubit-efficient recommendations.

Findings

Achieves similar recommendation accuracy with only five qubits.

Uses SVD and k-means for feature compression and dictionary learning.

Demonstrates effectiveness on real-world datasets.

Abstract

Modern recommenders describe each item with hundreds of sparse semantic tags, yet most quantum pipelines still map one qubit per tag, demanding well beyond one hundred qubits, far out of reach for current noisy-intermediate-scale quantum (NISQ) devices and prone to deep, error-amplifying circuits. We close this gap with a three-stage hybrid machine learning algorithm that compresses tag profiles, optimizes feature selection under a fixed qubit budget via QAOA, and scores recommendations with a Quantum semi-Random Forest (QsRF) built on just five qubits, while performing similarly to the state-of-the-art methods. Leveraging SVD sketching and k-means, we learn a 1000-atom dictionary ($>$97 \% variance), then solve a 2020 QUBO via depth-3 QAOA to select 5 atoms. A 100-tree QsRF trained on these codes matches full-feature baselines on ICM-150/500.