Quantum Semi-Random Forests for Qubit-Efficient Recommender Systems

2025-07-29

AI Summary

High-dimensional sparse semantic labels necessitate quantum recommendation systems with hundreds of qubits—exceeding the capacity of current Noisy Intermediate-Scale Quantum (NISQ) devices. Method: This paper proposes a three-stage hybrid framework: (1) constructing a highly discriminative atomic dictionary via SVD sketching and k-means clustering; (2) formulating feature selection as a Quadratic Unconstrained Binary Optimization (QUBO) problem and solving it efficiently using a depth-3 Quantum Approximate Optimization Algorithm (QAOA) constrained to only five qubits; and (3) designing a shallow-circuit-driven, quantum-enhanced semi-random forest (QsRF). Contribution/Results: On the ICM-150/500 datasets, QsRF achieves full-feature baseline performance using merely five qubits and 100 trees—reducing quantum resource requirements by two orders of magnitude. This significantly enhances NISQ compatibility and robustness while maintaining competitive accuracy.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

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.

Problem

• Compress sparse semantic tags for qubit-efficient quantum recommenders
• Optimize feature selection under limited qubit budget using QAOA
• Score recommendations accurately with few qubits using Quantum semi-Random Forest

Innovation

• Compresses tag profiles using SVD and k-means
• Optimizes feature selection via depth-3 QAOA
• Scores recommendations with Quantum semi-Random Forest