Application of quantum-inspired generative models to small molecular datasets

Abstract

Quantum and quantum-inspired machine learning has emerged as a promising and challenging research field due to the increased popularity of quantum computing, especially with near-term devices. Theoretical contributions point toward generative modeling as a promising direction to realize the first examples of real-world quantum advantages from these technologies. A few empirical studies also demonstrate such potential, especially when considering quantum-inspired models based on tensor networks. In this work, we apply tensor-network-based generative models to the problem of molecular discovery. In our approach, we utilize two small molecular datasets: a subset of $4989$ molecules from the QM9 dataset and a small in-house dataset of $516$ validated antioxidants from TotalEnergies. We compare several tensor network models against a generative adversarial network using different sample-based metrics, which reflect their learning performances on each task, and multiobjective performances using $3$ relevant molecular metrics per task. We also combined the output of the models and demonstrate empirically that such a combination can be beneficial, advocating for the unification of classical and quantum(-inspired) generative learning.

arXiv commentFirst version

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Quantum support vector machine for big data classification
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Generalization in quantum machine learning from few training data
• MolGAN: An implicit generative model for small molecular graphs
• Quantum-enhanced machine learning
• Unsupervised Generative Modeling Using Matrix Product States
• The Born Supremacy: Quantum Advantage and Training of an Ising Born Machine
• Performance comparison of optimization methods on variational quantum algorithms
• q-means: A quantum algorithm for unsupervised machine learning
• To quantum or not to quantum: towards algorithm selection in near-term quantum optimization
• Reinforcement Learning Assisted Recursive QAOA
• Hyperparameter Importance of Quantum Neural Networks Across Small Datasets
• Resource frugal optimizer for quantum machine learning
• Tabu-driven Quantum Neighborhood Samplers

Cited by in corpus (2)

• Hybrid quantum neural network for drug response prediction
• Hybrid quantum image classification and federated learning for hepatic steatosis diagnosis