Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Minimax Theory and its Applications

Quantum-Fuzzy Nonlinear Graph Neural Networks for Uncertainty-Aware High-Dimensional Data Representation and Intelligent Decision Making

Dr. Shanmugasundaram M, P. Sudheer, Dr Tamilselvi P, Rajeswari Manickam, K.S. Krishnapriya, Shanthi R, Dr. K. Aruna Bhaskar, R. Naveenkumar

Published Sep 22, 2026• 0 citations
OpenAlex

Abstract

The representation of data in high dimensions that are nonlinear leads to difficulties with uncertainty, complicated relations between variables and overlapping decision patterns which can lead to a reduction in reliability of the use of traditional learning models. The uncertainty-aware representation and intelligent decision making is proposed by this study, which proposes a Quantum-Fuzzy Nonlinear Graph Neural Network (QF NGNN). It fuses the fuzzy membership encoding of uncertain observations with nonlinear adaptive graph construction of dependency modeling, graph neural feature extraction, dimensionality-aware fusion, and the quantum-inspired amplitude-phase representation of classification. Different uncertainty levels (0%, 20%) and dimensions (10, 200) are used in the computational experiments with controlled high dimensional nonlinear data. The proposed model is compared against the MLP, GNN and the Fuzzy GNN baselines in terms of Accuracy, Macro-F1, RMSE, representation robustness and uncertainty sensitivity. The QF-NGNN baseline outperforms the other baseline models MLP, GNN and Fuzzy GNN under the aforementioned computational conditions with respect to accuracy, precision, recall and F1-score. The robustness analysis also supports this as improved performance retention with higher uncertainty while at the same time adding a moderate computational cost.This study suggests the feasibility of QF-NGNN for powerful uncertainty-aware high dimensional representation and intelligent decision-making support.

Related papers

Fuzzy Topological Graph Neural Networks for Modeling Nonlinear Quantum Systems under High Dimensional Uncertainty

Dr. N.Shanmuga Vadivu, S.Ilavazhagi Bala, Dr. G. Balaji +5 more

The dimensions of the state space of a nonlinearity in quantum system and the uncertainty in the interaction between the coupled variables make it more challenging to model such systems. Traditional neural networks and graph-learning algorithms are capable of modeling complicated nonlinear relationships, but tend to suffer a drop in performance in the presence of uncertain or harmful perturbations. This paper introduces a Fuzzy Topological Graph Neural Network (FT-GNN) in the strong modeling of nonlinear quantum systems in high-dimensional uncertainty. The fuzzy membership functions are used to describe the uncertain quantum-state variables to support ambiguity and perturbation of the state space. Only a fuzzy topological graph is then built to capture nonlinear dependencies and similarity relationships between the state dimensions. Topology-conscious graph neural propagation is used to learn the structured nonlinear representations of the resulting graph. To enhance robustness, a minimax optimization scheme is incorporated in the learning scheme, which minimizes model loss on worst-case perturbations in a bounded uncertainty set. The computational experiments are performed on various levels of uncertainty and compared to the traditional neural and graph-based models. Root means square error (RMSE), coefficient of determination (????2), Macro-F1 score, worst-case loss (WCL), and robustness retention (RR) are used to evaluate the performance. The quantitative data show better predictive fidelity, consistency in classification, reduced worst-case loss, and better performance retention as uncertainty increases, which validate FT-GNN as a powerful computational framework to model nonlinear quantum-systems.

Minimax Theory and its Applications•Sep 22, 2026•0 citations

Quantum-Enhanced Fuzzy Graph Neural Networks for Nonlinear Optimization and High-Dimensional Feature Representation

Dr. N.Shanmuga Vadivu, Swarna Kamalam Vaddi, Saravanan Chandrasekaran +5 more

Complex feature interactions along with uncertainty/variability and dimensionality increases as well as redundancy may lead to decreased representation quality and low optimization reliability, which is a challenge in high dimensional nonlinear optimization. In this paper, a robust feature representation and constrained nonlinear optimization framework to enhance the representation capability of features in a graph neural network (GNN) is proposed. The fuzzy modeling quantifies uncertain features with low, medium and high levels, and adaptive graph construction models the nonlinear dependencies between dimensions. Graph neural learning takes care of the extraction of the interaction-aware information, and then reduces the dimensionality in an aggregation fashion to get compact representation. A nonlinear optimization further enriches the learned features, which is preceded by a quantum-inspired amplitude–phase transformation. Computational evaluations are based on the 20 to 100 size range and uncertainty of 0 to 20%. QE-FGNN is evaluated and compared with MLP-NLO, GNN-NLO, and FGNN-NLO based on the following metrics: normalized optimization error, reconstruction error, feature preservation, constraint violation and computational time. The framework aims for optimization of good quality and features preservation while maintaining reasonable computation complexity, while also going for the future high-dimensional nonlinear optimization applications.

Minimax Theory and its Applications•Sep 22, 2026•0 citations

A Hierarchical Fused Quantum Fuzzy Neural Network for Image Classification

Shengyao Wu, Runze Li, Yan-Qi Song +3 more

Neural network is a powerful learning paradigm for data feature learning in the era of big data. However, most neural network models are deterministic models that ignore the uncertainty of data. Fuzzy neural networks are proposed to address this problem. FDNN is a hierarchical deep neural network that derives information from both fuzzy and neural representations, the representations are then fused to form representation to be classified. FDNN perform well on uncertain data classification tasks. In this paper, we proposed a novel hierarchical fused quantum fuzzy neural network (HQFNN). Different from classical FDNN, HQFNN uses quantum neural networks to learn fuzzy membership functions in fuzzy neural network. We conducted simulated experiment on two types of datasets (Dirty-MNIST and 15-Scene), the results show that the proposed model can outperform several existing methods. In addition, we demonstrate the robustness of the proposed quantum circuit.

arXiv:2403.09318•Mar 14, 2024•2 citations

Quantum-Assisted Hierarchical Fuzzy Neural Network for Image Classification

Shengyao Wu, Runze Li, Yanqi Song +3 more

Deep learning is a powerful technique for data-driven learning in the era of Big Data. However, most deep learning models are deterministic models that ignore the uncertainty of data. Fuzzy neural networks are proposed to tackle this type of problem. In this article, we proposed a novel quantum assisted hierarchical fuzzy neural network (QA-HFNN). Different from classical fuzzy neural networks, QA-HFNN uses quantum neural networks (QNNs) to learn fuzzy membership functions. The model is a multifeature fusion learning algorithm with a parallel structural design that integrates quantum and classical neural networks. The classical network is used to capture high-dimensional neural features, the QNNs are designed to capture fuzzy logic features of the data, then, the two features are fused to form the final features to be classified. The experiment is performed on a classical computer, and the quantum circuit is built through a simulated quantum environment. The results indicate that the accuracy of QA-HFNN can equal to or even surpass classical methods in image classification tasks. The quantum circuit utilizes only a single qubit which is easy to implement. In addition, the fidelity of quantum circuit in a quantum noise environment is assessed, demonstrating that QA-HFNN has strong robustness. The time and computational complexity of QNNs was analyzed, further proving the effectiveness of the model.

IEEE Transactions on Fuzzy Systems•Aug 19, 2024•35 citations

Dual-Qubit Hierarchical Fuzzy Neural Network for Image Classification: Enabling Relational Learning via Quantum Entanglement

Wenwei Zhang, Jintao Wang, Tianyu Ye +1 more

Classical deep neural network models struggle to represent data uncertainty and capture dependencies between features simultaneously, especially under fuzzy or noisy conditions. Although a quantum-assisted hierarchical fuzzy neural network (QA-HFNN) was proposed to learn fuzzy membership for each feature, it cannot model dependencies between features due to its single-qubit encoding. To address this, this paper proposes a dual-qubit hierarchical fuzzy neural network (DQ-HFNN), encoding feature pairs onto a pair of entangled qubits, which extends the single-feature fuzzy model to a joint fuzzy representation. By introducing quantum entanglement, the dual-qubit circuit can encode non-classical correlations, enabling the model to directly learn relationship patterns between feature pairs. Experiments on benchmarks show that DQ-HFNN demonstrates higher classification accuracy than QA-HFNN, as well as classical deep learning baselines. Furthermore, ablation studies after controlling for circuit depth and parameter counts show that the performance gain mainly stems from the relational modeling capability enabled by entanglement rather than enhanced expressivity. The proposed DQ-HFNN model exhibits high parameter efficiency and fast inference speed. Experiments under noisy conditions suggest that it is robust against noise and has the potential to be implemented on noisy intermediate-scale quantum devices.

quant-pharXiv:2512.13274•Dec 16, 2025•2 citations

Quantum-Enhanced Graph Neural Networks for Complex Decision Making in Cognitive Autonomous Systems

Sai Krishna Thota

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.

•Mar 16, 2026•0 citations
The representation of data in high dimensions that are nonlinear leads to difficulties with uncertainty, complicated relations between variables and overlapping decision patterns which can lead to a reduction in reliability of the use of traditional learning models. The uncertainty-aware representation and intelligent decision making is proposed by this study, which proposes a Quantum-Fuzzy Nonlinear Graph Neural Network (QF NGNN). It fuses the fuzzy membership encoding of uncertain observations with nonlinear adaptive graph construction of dependency modeling, graph neural feature extraction, dimensionality-aware fusion, and the quantum-inspired amplitude-phase representation of classification. Different uncertainty levels (0%, 20%) and dimensions (10, 200) are used in the computational experiments with controlled high dimensional nonlinear data. The proposed model is compared against the MLP, GNN and the Fuzzy GNN baselines in terms of Accuracy, Macro-F1, RMSE, representation robustness and uncertainty sensitivity. The QF-NGNN baseline outperforms the other baseline models MLP, GNN and Fuzzy GNN under the aforementioned computational conditions with respect to accuracy, precision, recall and F1-score. The robustness analysis also supports this as improved performance retention with higher uncertainty while at the same time adding a moderate computational cost.This study suggests the feasibility of QF-NGNN for powerful uncertainty-aware high dimensional representation and intelligent decision-making support.
The dimensions of the state space of a nonlinearity in quantum system and the uncertainty in the interaction between the coupled variables make it more challenging to model such systems. Traditional neural networks and graph-learning algorithms are capable of modeling complicated nonlinear relationships, but tend to suffer a drop in performance in the presence of uncertain or harmful perturbations. This paper introduces a Fuzzy Topological Graph Neural Network (FT-GNN) in the strong modeling of nonlinear quantum systems in high-dimensional uncertainty. The fuzzy membership functions are used to describe the uncertain quantum-state variables to support ambiguity and perturbation of the state space. Only a fuzzy topological graph is then built to capture nonlinear dependencies and similarity relationships between the state dimensions. Topology-conscious graph neural propagation is used to learn the structured nonlinear representations of the resulting graph. To enhance robustness, a minimax optimization scheme is incorporated in the learning scheme, which minimizes model loss on worst-case perturbations in a bounded uncertainty set. The computational experiments are performed on various levels of uncertainty and compared to the traditional neural and graph-based models. Root means square error (RMSE), coefficient of determination (????2), Macro-F1 score, worst-case loss (WCL), and robustness retention (RR) are used to evaluate the performance. The quantitative data show better predictive fidelity, consistency in classification, reduced worst-case loss, and better performance retention as uncertainty increases, which validate FT-GNN as a powerful computational framework to model nonlinear quantum-systems.
Complex feature interactions along with uncertainty/variability and dimensionality increases as well as redundancy may lead to decreased representation quality and low optimization reliability, which is a challenge in high dimensional nonlinear optimization. In this paper, a robust feature representation and constrained nonlinear optimization framework to enhance the representation capability of features in a graph neural network (GNN) is proposed. The fuzzy modeling quantifies uncertain features with low, medium and high levels, and adaptive graph construction models the nonlinear dependencies between dimensions. Graph neural learning takes care of the extraction of the interaction-aware information, and then reduces the dimensionality in an aggregation fashion to get compact representation. A nonlinear optimization further enriches the learned features, which is preceded by a quantum-inspired amplitude–phase transformation. Computational evaluations are based on the 20 to 100 size range and uncertainty of 0 to 20%. QE-FGNN is evaluated and compared with MLP-NLO, GNN-NLO, and FGNN-NLO based on the following metrics: normalized optimization error, reconstruction error, feature preservation, constraint violation and computational time. The framework aims for optimization of good quality and features preservation while maintaining reasonable computation complexity, while also going for the future high-dimensional nonlinear optimization applications.
Neural network is a powerful learning paradigm for data feature learning in the era of big data. However, most neural network models are deterministic models that ignore the uncertainty of data. Fuzzy neural networks are proposed to address this problem. FDNN is a hierarchical deep neural network that derives information from both fuzzy and neural representations, the representations are then fused to form representation to be classified. FDNN perform well on uncertain data classification tasks. In this paper, we proposed a novel hierarchical fused quantum fuzzy neural network (HQFNN). Different from classical FDNN, HQFNN uses quantum neural networks to learn fuzzy membership functions in fuzzy neural network. We conducted simulated experiment on two types of datasets (Dirty-MNIST and 15-Scene), the results show that the proposed model can outperform several existing methods. In addition, we demonstrate the robustness of the proposed quantum circuit.
Deep learning is a powerful technique for data-driven learning in the era of Big Data. However, most deep learning models are deterministic models that ignore the uncertainty of data. Fuzzy neural networks are proposed to tackle this type of problem. In this article, we proposed a novel quantum assisted hierarchical fuzzy neural network (QA-HFNN). Different from classical fuzzy neural networks, QA-HFNN uses quantum neural networks (QNNs) to learn fuzzy membership functions. The model is a multifeature fusion learning algorithm with a parallel structural design that integrates quantum and classical neural networks. The classical network is used to capture high-dimensional neural features, the QNNs are designed to capture fuzzy logic features of the data, then, the two features are fused to form the final features to be classified. The experiment is performed on a classical computer, and the quantum circuit is built through a simulated quantum environment. The results indicate that the accuracy of QA-HFNN can equal to or even surpass classical methods in image classification tasks. The quantum circuit utilizes only a single qubit which is easy to implement. In addition, the fidelity of quantum circuit in a quantum noise environment is assessed, demonstrating that QA-HFNN has strong robustness. The time and computational complexity of QNNs was analyzed, further proving the effectiveness of the model.
Classical deep neural network models struggle to represent data uncertainty and capture dependencies between features simultaneously, especially under fuzzy or noisy conditions. Although a quantum-assisted hierarchical fuzzy neural network (QA-HFNN) was proposed to learn fuzzy membership for each feature, it cannot model dependencies between features due to its single-qubit encoding. To address this, this paper proposes a dual-qubit hierarchical fuzzy neural network (DQ-HFNN), encoding feature pairs onto a pair of entangled qubits, which extends the single-feature fuzzy model to a joint fuzzy representation. By introducing quantum entanglement, the dual-qubit circuit can encode non-classical correlations, enabling the model to directly learn relationship patterns between feature pairs. Experiments on benchmarks show that DQ-HFNN demonstrates higher classification accuracy than QA-HFNN, as well as classical deep learning baselines. Furthermore, ablation studies after controlling for circuit depth and parameter counts show that the performance gain mainly stems from the relational modeling capability enabled by entanglement rather than enhanced expressivity. The proposed DQ-HFNN model exhibits high parameter efficiency and fast inference speed. Experiments under noisy conditions suggest that it is robust against noise and has the potential to be implemented on noisy intermediate-scale quantum devices.
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.