Implementation of Trained Factorization Machine Recommendation System on Quantum Annealer

2022/10/24 by Chen-Yu Liu, Hsin-Yu Wang, Liu, Chen-Yu +7 · 3 citations
Computer Science · #Cloud Computing and Resource Management #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Quantum Computing Algorithms and Architecture #Quantum Physics (quant-ph) #Stochastic Gradient Optimization Techniques

paper · pdf · doi:10.48550/arxiv.2210.12953

openalex publication_date 2022/10/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Factorization Machine (FM) is the most commonly used model to build a recommendation system since it can incorporate side information to improve performance. However, producing item suggestions for a given user with a trained FM is time-consuming. It requires a run-time of O((N_m log N_m)²), where N_m is the number of items in the dataset. To address this problem, we propose a quadratic unconstrained binary optimization (QUBO) scheme to combine with FM and apply quantum annealing (QA) computation. Compared to classical methods, this hybrid algorithm provides a faster than quadratic speedup in finding good user suggestions. We then demonstrate the aforementioned computational advantage on current NISQ hardware by experimenting with a real example on a D-Wave annealer.

Cited by

• Effectiveness of cardinality-return weighted maximum independent set approach for financial portfolio optimization
• Quantum Relational Knowledge Distillation
• Subsampling Factorization Machine Annealing

Related

• Performance-Driven QUBO for Recommender Systems on Quantum Annealers
• CRUISE on Quantum Computing for Feature Selection in Recommender Systems
• Are Quantum Computers Practical Yet? A Case for Feature Selection in Recommender Systems using Tensor Networks
• Black-box optimization using factorization and Ising machines
• Quantum Annealing for Machine Learning: Applications in Feature Selection, Instance Selection, and Clustering