# Quantum Semi-Random Forests for Qubit-Efficient Recommender Systems

arXiv: https://arxiv.org/abs/2508.00027 · HTML: https://mlsanity.com/paper/2508.00027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Builds on (most cited first, 6 of 6)

- [Feature Selection on Quantum Computers](https://mlsanity.com/paper/2203.13261/) (2022)
- [Feature Selection for Recommender Systems with Quantum Computing](https://mlsanity.com/paper/2110.05089/) (2021)
- [Towards Feature Selection for Ranking and Classification Exploiting Quantum Annealers](https://mlsanity.com/paper/2205.04346/) (2022)
- [Dictionary Learning for Massive Matrix Factorization](https://mlsanity.com/paper/1605.00937/) (2016)
- [Quantum Annealing vs. QAOA: 127 Qubit Higher-Order Ising Problems on NISQ Computers](https://mlsanity.com/paper/2301.00520/) (2023)
- [Feature Selection for Classification with QAOA](https://mlsanity.com/paper/2211.02861/) (2022)

## Abstract (arXiv)

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.