The study explores the integration of quantum-enhanced feature mapping and optimization within Graph Neural Networks (GNNs) for molecular classification tasks. Utilizing IBM's Qiskit platform, we implement Variational Quantum Circuits (VQCs) to transform classical molecular features into quantum states, capturing complex correlations through quantum entanglement. Additionally, the Quantum Approximate Optimization Algorithm (QAOA) is employed for hyperparameter tuning to enhance model convergence and performance. Comparative analyses against traditional machine learning models demonstrate the superiority of the quantum-enhanced GNN, highlighting the potential of quantum computing in advancing molecular property prediction.
The study explores the integration of quantum-enhanced feature mapping and optimization within Graph Neural Networks (GNNs) for molecular classification tasks. Utilizing IBM's Qiskit platform, we implement Variational Quantum Circuits (VQCs) to transform classical molecular features into quantum states, capturing complex correlations through quantum entanglement. Additionally, the Quantum Approximate Optimization Algorithm (QAOA) is employed for hyperparameter tuning to enhance model convergence and performance. Comparative analyses against traditional machine learning models demonstrate the superiority of the quantum-enhanced GNN, highlighting the potential of quantum computing in advancing molecular property prediction.
Quantum computing has been a prominent research area for decades, inspiring transformative fields such as quantum simulation, quantum teleportation, and quantum machine learning (QML), which are undergoing rapid development. Within QML, hybrid classical-quantum algorithms like Quantum Neural Networks (QNNs) and Variational Quantum Classifiers (VQCs) have shown promise in leveraging quantum circuits and classical optimizers to classify classical data efficiently. Simultaneously, classical machine learning has made significant strides in graph classification, employing Graph Neural Networks (GNNs) to analyze systems ranging from large-scale structures like the Large Hadron Collider to molecular and biological systems like proteins and DNA. Combining the advancements in quantum computing and graph classification presents a unique opportunity to develop quantum algorithms capable of extracting features from graphs and performing their classification effectively. In this paper, we propose a novel quantum encoding framework for graph classification using VQCs. Unlike existing approaches such as PCA-VQC, which rely on dimensionality reduction techniques like Principal Component Analysis (PCA) and may lead to information loss, our method preserves the integrity of graph data. Furthermore, our encoding approach is optimized for Noise-Intermediate Scale Quantum (NISQ) devices, requiring a limited number of qubits while achieving comparable or superior classification performance to PCA-VQC. By constructing slightly more complex circuits tailored for graph encoding, we demonstrate that VQCs can effectively classify graphs within the constraints of current quantum hardware.
Graph Neural Networks (GNNs) are now one of the key tools to model relational and non-Euclidean data in multiagent systems, infrastructure networks and even molecular modeling applications. Nevertheless, in very dense or noisy graph topologies, classical message-passing architectures may experience scalability and representational degeneration, especially due to over-smoothing and insufficient higher-order dependency information. The recent developments in quantum machine learning indicate that hybrid quantum-classical models can also provide an alternative feature representation by projecting relational data to parameterized quantum circuits. This article presents a Quantum-Enhanced Graph Neural Network (QGNN) architecture that extends variational quantum circuits with graph learning pipelines, based on classical learning. Parameters are represented as parameterized qubits, and relational dependencies are represented as structured entanglement mappings. We benchmark the regimes where quantum-enhanced relational encoding proves to be more robust and stable through the swarm coordination, molecular property prediction, and financial transaction network. We also elaborate on the issue of scalability, hardware issues, and practical aspects of near-term hybrid implementations and give a critical view of the changing role of quantum methods in computational intelligence systems.
Graph Neural Networks (GNNs) are now one of the key tools to model relational and non-Euclidean data in multiagent systems, infrastructure networks and even molecular modeling applications. Nevertheless, in very dense or noisy graph topologies, classical message-passing architectures may experience scalability and representational degeneration, especially due to over-smoothing and insufficient higher-order dependency information. The recent developments in quantum machine learning indicate that hybrid quantum-classical models can also provide an alternative feature representation by projecting relational data to parameterized quantum circuits. This article presents a Quantum-Enhanced Graph Neural Network (QGNN) architecture that extends variational quantum circuits with graph learning pipelines, based on classical learning. Parameters are represented as parameterized qubits, and relational dependencies are represented as structured entanglement mappings. We benchmark the regimes where quantum-enhanced relational encoding proves to be more robust and stable through the swarm coordination, molecular property prediction, and financial transaction network. We also elaborate on the issue of scalability, hardware issues, and practical aspects of near-term hybrid implementations and give a critical view of the changing role of quantum methods in computational intelligence systems.
Quantum graph neural networks (QGNNs) have shown promise in leveraging quantum computing to enhance graph-structured data learning, yet they are typically limited to homogeneous graphs. In this paper, we introduce the quantum heterogeneous graph neural network (QHGNN), which integrates heterogeneity as an inductive bias within quantum circuits, enabling effective learning on heterogeneous graphs. By encoding diverse node and edge types directly into the quantum circuit architecture, QHGNN can capture complex relationships intrinsic to heterogeneous molecular data. Our experiments utilize PTC datasets to assess the performance of QHGNN in molecular property prediction tasks, showcasing superior prediction accuracy and efficiency, along with enhanced noise resilience when compared to existing QGNN models.
With the advancement of quantum computing in the Noisy Intermediate-Scale Quantum (NISQ) era, hybrid quantum-classical algorithms have emerged as promising approaches for addressing certain machine learning tasks. This study investigates the Variational Quantum Classifier (VQC), a hybrid model that integrates parameterized quantum circuits with classical optimization routines, implemented via IBM’s Qiskit framework. We provide a detailed account of the VQC architecture, including feature encoding, ansatz construction, and optimization methodology. To assess its performance, we conduct a comparative analysis between VQC and classical Support Vector Classifiers (SVC) across synthetic and real-world datasets, including Iris and a binary-filtered version of MNIST. Experimental results reveal that classical models consistently achieve higher accuracy and faster training times. However, the VQC demonstrates functional viability, particularly under noise-free conditions and reduced-dimensionality settings. These findings underscore the current limitations of quantum models while highlighting the potential of VQC as a proof-of-concept for quantum-enhanced learning as quantum hardware matures.
This study presents a comparative evaluation of Artificial Neural Networks (ANNs) and Variational Quantum Circuits (VQCs) for biomedical classification, using the Wisconsin Breast Cancer Diagnostic dataset. Both models were optimized using Bayesian hyperparameter tuning via Optuna to ensure a fair performance comparison. The ANN achieved high predictive accuracy (98.2%), F1 score (98.2%), and Area Under the Curve (AUC) (0.98), exhibiting stable convergence and efficient training. The VQC, though trained under classical simulation, attained a respectable accuracy of 86.5% and an AUC of 0.85, with notably strong recall (99.1%) for malignant cases, highlighting its potential in scenarios requiring high sensitivity. Loss curves, confusion matrices, and hyperparameter importance visualizations were used to interpret each model’s training behaviour and decision boundaries. While classical models remain superior in current biomedical classification tasks, VQCs offer promising computational advantages and potential scalability for complex, high-dimensional datasets. This work provides early benchmarks for quantum-classical comparisons in biomedical machine learning and offers guidance for future implementations as quantum hardware becomes more accessible.