Quantum Machine Learning: Diverse Perspectives on Application Scenarios - Dissertation Defence

Aug 4, 2026

Upload by Aurelia

Quantum Machine Learning explores how quantum computing can alleviate the bottlenecks faced by classical machine learning while enabling new information representations and processing methods. The thesis focuses on application and method innovation for structured data, studying theoretical models and practical deployments across agricultural remote sensing, graph neural networks, and hyperdimensional computing. It proposes a quantum-classical hybrid framework for imbalanced small-sample data, a CTQW-enhanced GNN for graph structure learning, and native-to-quantum-enhanced HDC strategies using quantum circuits and quantum feature mechanisms. Experimental evaluations across real and simulation platforms validate adaptability, scalability, and effectiveness, demonstrating improved accuracy, robustness, and generalization, supported by end-to-end quantum circuit design and closed-loop validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages157

Reading Time6 h 36 min

AccessFree to download

Abstract

Agricultural remote sensing: cropland classification and yield prediction

Graph structure learning with CTQW and GNN

Hyperdimensional computing: native quantum-state HDC and quantum-enhanced HDC

PhD-FSTM-2025-081 The Faculty of Science, Technology and Medicine DISSERTATION Defence held on 08/07/2025 in Luxembourg to obtain the degree of DOCTEUR DE L’UNIVERSIT ´E DU LUXEMBOURG EN INFORMATIQUE by Yangjie XU Born on 18 June 1994 in Jiangsu (China) Quantum Machine Learning: Diverse Perspectives on Application Scenarios Dissertation Defence Committee: Dr. Radu STATE, Dissertation Supervisor Professor, SnT, University of Luxembourg Dr. Rapha¨el FRANK, Chairman Assistant Professor, SnT, University of Luxembourg Dr. Hui HUANG Research Scientist, SnT, University of Luxembourg Dr. R´emi BADONNEL Professor, TELECOM Nancy Engineering School, University of Lorraine, France Dr. Kai LI Senior Research Scientist, CISTER Research Unit at ISEP/IPP, Lisbon, Portugal Affidavit I hereby confirm that the PhD thesis entitled “Quantum Machine Learning: Diverse Perspectives on Application Scenarios ” has been written independently and without any other sources than cited. Luxembourg, Yangjie XU Abstract In recent years, quantum computing, as a potential way to break the bottleneck of Moore’s Law, has gradually shown its unique advantages in the field of machine learning. Not only can it bring exponential or polynomial acceleration in some specific tasks, it also provides entirely new ways of representing and processing information. Focusing on the core theme of application and method innovation of quantum machine learning in structured data, this thesis systematically studies the theoretical models and practical applications of quantum computing in many sub-fields such as agricultural remote sensing, graph neural networks, and hyperdimensional computing, and explores the adaptability, scalability, and effectiveness of quantum models in real-world tasks. Firstly, in the cropland classification and yield prediction task, this study identifies that traditional neural networks tend to underperform when facing imbalanced and small-sample remote sensing data, often misclassifying minority crop types. To address this, we propose a quantum-classical hybrid recognition framework that integrates quantum feature mapping with classical neural networks. After incorporating quantum feature encoding, we observe a significant improvement in classification performance, especially in cases involving subtle field boundaries and heterogeneous textures. The quantum-enhanced model demonstrates superior accuracy, robustness, and generalization compared to its classical counterpart, validating the advantage of leveraging quantum representations in real-world agricultural datasets. The second part focuses on the learning of graph structure data and proposes to embed the Continuous Time Quantum Walk (CTQW) into the Graph Neural Network (GNN) architecture. This method not only preserves the global interference characteristic of quantum states but also realizes the efficient modeling of graph topology through the spectral graph methods. Experiments show that the proposed method is superior to many classical graph learning models in tasks such as node classification and graph structure inference. The third and fourth components of this thesis collectively explore quantum ap- proaches to hyperdimensional computing (HDC), establishing a progressive transition from native quantum-state-based implementation to quantum-enhanced HDC strategies. Initially, we investigate the intrinsic mathematical correspondence between quantum states and high-dimensional hypervectors, and propose a novel quantum-state-based high-dimensional encoding method. This method is realized through quantum circuits capable of generating hypervectors with controllable entropy, thereby implementing essential HDC operations, such as classification and memory reconstruction, on real quantum hardware. This marks the first successful migration of core HDC mechanisms into a fully quantum-native framework. Building upon this foundation, we furt

FAQs

What problem does the thesis address in agricultural remote sensing tasks?

It targets cropland classification and yield prediction where traditional neural networks underperform on imbalanced and small-sample remote sensing data, often misclassifying minority crop types.

How is quantum information integrated into graph neural networks in this work?

The thesis embeds Continuous Time Quantum Walk (CTQW) into the Graph Neural Network (GNN) architecture, preserving global quantum interference while enabling efficient spectral modeling of graph topology.

What are the two main quantum approaches to hyperdimensional computing proposed in the thesis?

It first develops a quantum-state-based high-dimensional encoding method to migrate core HDC mechanisms into a fully quantum-native framework, then introduces a quantum-enhanced HDC strategy that leverages key quantum features to improve efficiency and expressivity under noisy sensing environments.

Aug 4, 2026

Upload by Aurelia