To accelerate the process of materials design, materials science has increasingly used data driven techniques to extract information from collected data. Specially, machine learning (ML) algorithms, which span the ML discipline, have demonstrated ability to predict various properties of materials with the level of accuracy similar to explicit calculation of quantum mechanical theories, but with significantly reduced run time and computational resources. Within ML, graph neural networks have emerged as an important algorithm within the field of machine learning, since they are capable of predicting accurately a wide range of important physical, chemical and electronic properties due to their higher learning ability based on the graph representation of material and molecular descriptors through the aggregation of information embedded within the graph. In parallel with the development of state of the art classical machine learning applications, the fusion of quantum computing and machine learning have created a new paradigm where classical machine learning model can be augmented with quantum layers which are able to encode high dimensional data more efficiently. Leveraging the structure of existing algorithms, we developed a unique and novel gradient free hybrid quantum classical convoluted graph neural network (HyQCGNN) to predict formation energies of perovskite materials. The performance of our hybrid statistical model is competitive with the results obtained purely from a classical convoluted graph neural network, and other classical machine learning algorithms, such as XGBoost. Consequently, our study suggests a new pathway to explore how quantum feature encoding and parametric quantum circuits can yield drastic improvements of complex ML algorithm like graph neural network.
This paper presents a novel quantum algorithm designed to enhance machine learning precision through the synergistic optimization of multi-scale geometric information. Traditional machine learning approaches often rely on single-scale data, limiting their potential for robust and accurate models. Our algorithm introduces a multi-scale geometric information encoding technique, utilizing quantum entanglement and quantum gates to facilitate coordinated optimization of diverse geometric features. The core mechanism focuses on leveraging the inherent correlations and patterns within multi-scale datasets to improve model performance across various levels of complexity. We demonstrate the algorithm's effectiveness through a series of simulations and preliminary experiments, showcasing significant improvements in accuracy compared to existing state-of-the-art machine learning models. This work offers a promising path towards more sophisticated and data-driven machine learning solutions.
This paper presents a novel approach to quantum machine learning leveraging the concept of inherent data distribution heterogeneity. We propose a quantum-enhanced algorithm designed to automatically adjust the parameters of machine learning models based on the distribution of data points. This method, termed "Heterogeneous Information Driven Quantum Machine Learning," aims to improve model generalization by intelligently adapting to the inherent variability within the data. The core mechanism involves utilizing quantum entanglement and superposition to effectively represent and analyze data distribution, allowing for a dynamic and informed parameter tuning process. We demonstrate the efficacy of this approach through simulations and preliminary experiments, highlighting its potential to overcome limitations of traditional machine learning techniques.