Hybridization of Quantum Information and Machine Learning

Rikard Wadman

Michael Vitz, Hamed Mohammadbagherpoor, Samarth Sandeep +3 more

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.

Maiyuren Srikumar, Charles D. Hill, Lloyd C. L. Hollenberg

Abstract Quantum machine learning (QML) is a rapidly growing area of research at the intersection of classical machine learning and quantum information theory. One area of considerable interest is the use of QML to learn information contained within quantum states themselves. In this work, we propose a novel approach in which the extraction of information from quantum states is undertaken in a classical representational-space, obtained through the training of a hybrid quantum autoencoder (HQA). Hence, given a set of pure states, this variational QML algorithm learns to identify—and classically represent—their essential distinguishing characteristics, subsequently giving rise to a new paradigm for clustering and semi-supervised classification. The analysis and employment of the HQA model are presented in the context of amplitude encoded states—which in principle can be extended to arbitrary states for the analysis of structure in non-trivial quantum data sets.

Zeph Hardie

A. S. Wilson

Jincheng Zhang

This paper proposes a novel symbiotic quantum-classical hybrid learning framework designed to enhance machine learning performance. The core idea revolves around establishing a dynamic, synergistic relationship between quantum and classical computational resources. The framework leverages the strengths of both paradigms: the quantum processor handles computationally intensive tasks, particularly kernel calculations within machine learning algorithms, while the classical processor manages optimization, control, and data handling. Unlike traditional static hybrid approaches that often operate in isolation, this symbiotic architecture allows for adaptive and real-time communication and feedback between the two systems. We present a detailed mathematical formulation of the proposed system, outlining the key components, data flow, and optimization strategies. The framework's ability to dynamically adjust the workload distribution based on the computational demands of each system represents a significant advancement in hybrid quantum-classical learning. We demonstrate, through theoretical analysis, the potential for improved convergence rates and overall learning efficiency compared to purely classical or static hybrid methods. The presented model incorporates key concepts from quantum information theory, optimization algorithms, and machine learning, aiming to provide a robust and scalable approach to complex learning problems. ---