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

Journal of Quantum Artificial Intelligence

Noise-Resilient Variational Quantum Transformers for Sequence Modeling in the NISQ Era

Bambang Harimanto

Published May 1, 2026• 0 citations
Publisher

Abstract

Near-term quantum hardware offers an opportunity to augment sequence modeling, yet NISQ noise and finite-shot measurement variance often erase gains when quantum components are invoked repeatedly across long contexts. This paper proposes a Noise-Resilient Variational Quantum Transformer (VQT) that inserts shallow, connectivity-aware variational circuits selectively into transformer attention scoring, while retaining classical residual pathways for stability and scalability. The training objective is noise-aware, optimizing expected loss under sampled noise realizations, and inference applies tiered mitigation (always-on readout correction and selective zero-noise extrapolation for critical blocks). Across controlled sequence modeling and sequence-level classification evaluations, VQT improves endpoint quality and robustness under increasing noise. Relative to a parameter-matched classical transformer, the full VQT reduces perplexity from 26.8 to 24.2 (−2.6, −9.7%) and bits-per-character from 1.42 to 1.34 (−0.08), while increasing macro-F1 from 0.812 to 0.844 (+0.032, +3.9%). Calibration also improves, with ECE decreasing from 0.064 to 0.048 (−25%). Under a high-noise condition (noise strength 0.10), VQT with mitigation achieves perplexity 32.6 versus 36.2 for the classical baseline (−3.6, −9.9%) and shows a flatter degradation slope (84.0 vs 94.0) and lower robustness AUC (2.86 vs 3.04). Ablations confirm that removing noise-aware training increases the robustness penalty (Δperplexity under noise) from 8.4 to 12.1, while removing mitigation increases it to 15.3, indicating complementary contributions from optimization and mitigation. The approach remains feasible under bounded quantum cost, exemplified by 160 circuit executions per batch at 512 shots per execution.

DOI
10.63913/jqai.v1i1.2

Related papers

Adaptive Noise-Aware Variational Quantum Classifier for Robust Machine Learning on NISQ Devices

Vinodh Kumar S, Pravin P

The execution of Variational Quantum Algorithms on Noisy Intermediate-Scale Quantum hardware is severely impacted by hardware noise variations over time and decoherence. This work introduces an Adaptive Noise-Aware Variational Quantum Classifier (ANAVQC) that integrates Zero-Noise Extrapolation (ZNE) dynamically into the training loop to counter variations. The framework approximates the instantaneous depolarizing noise from calibration and adapts noise scaling and linear extrapolation to estimate noise-free expectation values at training. A two-qubit parameterized quantum circuit is built and simulated in MATLAB, with the inclusion of stochastic gradient descent coupled with parameter-shift-based gradients. The model is conditioned on a synthetic binary classification data under a time-varying depolarizing noise profile and exhibits improved convergence stability and classification accuracy over non-adaptive methods. The simulation results identify that adaptive ZNE increases model robustness against time-varying noise and offers a scalable route to reliable quantum machine learning on practical NISQ hardware. The current ANAVQC scheme is extendable to multi-qubit platforms and practical quantum backends for the purposes of future experimental testing.

International Conference on Intelligent Computing and Automation for Sustainable Solutions (ICASS)•Feb 12, 2026•0 citations

NAVQNN: Noise-Aware adaptive variational quantum neural network framework for NISQ devices

Bommisetti Rakesh

The noise of quantum-enhanced learning there is a potential of quantum-enhanced learning with noisy intermediate-scale quantum (NISQ) devices, which is limited by hardware noise and finding useful circuit architectures. In this paper, a Noise-Aware Adaptive Variational Quantum Neural Network (NAVQNN) structure is proposed, which is capable of solving such issues simultaneously. The angle encoding of classical feature vectors (variance, skewness, kurtosis, entropy) of cheque images into quantum states is done on a shallow variational circuit. The noise-sensitive adaptive ansatz generator, in turn, develops the circuit layer-by-layer by picking the new parameterized gate blocks based on their validation loss with an explicit noise model and discouraging depth and two-qubit interactions in their cost functional. The ensuing variational quantum classifier is then trained by a hybrid quantum-classical optimization cycle based on the parameter-shift rule. The experiments on the UCI banknote authentication dataset indicate the usefulness of the proposed approach with the accuracy of 0.9913, precision of 0.9869, recall of 0.9934, F1-score of 0.9902, and ROC-AUC of 0.9998. Figures of prediction score densities, decision boundary, and live inference outputs are additional proof that NAVQNN can gain a strong and well-calibrated decision-making function in compliance with practical NISQ requirements. These findings suggest that noise-conscious adaptive variational circuits can be a useful foundation for quantum-enhanced financial fraud detection and various classification problems.

ARPN Journal of Engineering and Applied Sciences•Aug 20, 2026•0 citations

Quantum Noise Mitigation with Adaptive Zero-Noise Extrapolation: A Contextual Multi-Armed Bandits Approach

Ratun Rahman, Dinh C. Nguyen

Variational quantum circuits (VQCs) are central to near-term quantum computing, yet their practical deployment is severely hindered by noise. While existing error mitigation methods, such as zero-noise extrapolation (ZNE), typically assume static noise, real noisy intermediate-scale quantum (NISQ) systems exhibit dynamic, time-varying noise that remains largely unaddressed. To overcome this critical gap, our work introduces a novel adaptive noise mitigation framework for VQCs that integrates ZNE with contextual multi-armed bandits (CMAB), enabling dynamic, context-aware selection of circuit-folding levels based on ansatz parameters (e.g., depth, parameter count) and the evolving noise environment. Unlike fixed-fold or heuristic ZNE, our approach uses online adaptation to improve the accuracy of ZNE and reduce redundant quantum circuit executions. Our extensive simulations and experiments on real quantum hardware reveal the following important properties: (i) deeper VQCs accumulate noise, degrading accuracy and increasing the number of quantum circuit executions; (ii) ZNE restores estimator fidelity when the folding level is chosen appropriately; and (iii) CMAB-guided folding cuts quantum circuit execution round trips by up to 40\%, bytes exchanged by up to 35\%, and end-to-end cost by up to 30\% under a 10~Mbps budget, with up to 6.9\% higher estimator fidelity (CIFAR-10, depth 3, noise band $η=0.05$), versus fixed-fold and grid-search ZNE. These results demonstrate substantial performance gains over existing noise mitigation methods, underscoring the effectiveness of our design in supporting robust noise mitigation for VQCs. The source code is also publicly released to support reproducibility.

quant-pharXiv:2608.06426•IEEE Journal on Selected Areas in Communications•Aug 7, 2026•2 citations

Noise-Aware Adaptive Variational Quantum Neural Network (NAVQNN) For Robust NISQ-Era Banknote Authentication

Bommisetti Rakesh, G.Murali

Noise and limited circuit depth remain major obstacles for deploying quantum machine learning models on noisy intermediate-scale quantum (NISQ) devices. Variational quantum neural networks (VQNNs) are promising for near-term learning, but their performance strongly depends on ansatz design and training stability under realistic noise. In this paper, we propose a Noise-Aware Adaptive Variational Quantum Neural Network (NAVQNN) for supervised binary classification. NAVQNN combines angle-based quantum encoding with a variational classifier whose circuit structure is grown adaptively from a candidate block pool using a noise-aware selection criterion that evaluates validation loss under a depolarizing noise model and penalizes hardware cost (depth and entangling gates). The model is trained in a hybrid quantum–classical loop using parameter-shift gradients and the Adam optimizer. Experiments on the UCI Banknote Authentication dataset demonstrate strong classification performance, achieving 99.13% accuracy and AUC = 0.9998 under NISQ-like noisy simulation, with consistently high precision, recall, and F1-score. These results indicate that noise-aware adaptive circuit construction can reduce dependence on hand-crafted ansätze while maintaining reliable performance in near-term quantum learning settings.

International Conference on Knowledge Engineering and Communication Systems (ICKECS)•Apr 24, 2026•0 citations

Noise-Aware QML: Adaptive Noise-Regularized Variational Quantum Circuits for Parameter-Efficient Tabular Anomaly Detection

Saksham Garg, Dhruti A, Panchadip Bhattacharjee +3 more

Anomaly detection on high-dimensional tabular data requires models that are simultaneously compact, robust to noise, and interpretable, which are not met well by traditional ensemble learning approaches under strict parameter budgets. This work introduces NoiseAware-QML, a Variational Quantum Circuit (VQC) approach that incorporates a learnable noise parameter$\sigma$directly into the quantum ansatz, allowing the circuit to adaptively learn noise robustness during optimization through the reparameterization trick. The proposed 4-qubit, 4-layer VQC requires only 54 trainable parameters, a$715 \times$reduction over Random Forest and$91 \times$reduction over XGBoost, while maintaining a multi-seed mean ROC-AUC of$0.8366 \pm 0.0083$(95% CI: [0.8252, 0.8446]) on UNSW-NB15. Three robustness advantages with respect to parameter budget are formally established: (i) robustness to noise-1.84% AUC loss at$\sigma=0.10$compared to 4.12% for Random Forest (2.24× better) and 2.41% for a comparable-sized Dropout-MLP$(1.31 \times$better); (ii) calibration-$\mathbf{E C E}=0.0726$, improving over Random Forest (0.1127) and MLP (0.1151) by 36-37% without calibration correction; (iii) cross-dataset stability-only 5.36% AUC loss on NSL-KDD compared to 8.47% for Random Forest. Ablation study over three seeds verifies that adaptive noise regularization always improves over all variants by$\approx 0.089$AUC. Explainability through quantum-native means, per-gate gradientnorm heatmaps, and Bloch sphere analysis, demonstrates that the second-highest PCA variance component is actually harmful to anomaly detection, a result hidden from classical feature selection. Simulation-based deployment analysis confirms that the model generalizes to simulated NISQ hardware settings with AUC degradation of less than 2%.

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)•Jul 1, 2026•0 citations

Noise-Resilient Optimization of Parameterized Quantum Circuits for Near-Term Quantum Devices

Deepika D, K Vanishree, Munishamaiah Krishna

Abstract Noisy Intermediate-Scale Quantum (NISQ) devices are near-term quantum computing devices that inherently suffer from imperfect gate implementation, decoherence, and measurement noise. The main type of variational quantum algorithms(VQAs) is based on Parameterized Quantum Circuits (PQCs), which, however, face practical challenges due to optimization instability of optimization caused by noise and reduced performance. In this paper, we suggest a comprehensive noise-resilient optimization framework for PQCs, which explicitly incorporates noise-resilient circuit architecture design, incorporating noise-aware training strategies into the variational optimization loop. The framework uses circuit structures that are efficient in depth and are hardware compatible in addition to adaptive optimizer choice, stochastic optimization, and averaging as a part of repeated measurement to reduce the impacts of realistic noise. Large-scale experiments are performed with different amounts of qubits, depths of the circuit and noise strengths with realistic noise models. The findings indicate that the convergence rate is faster, the stability is increased, the variability of run-to-run variability is minimized, and other robustness is better than the noise-unaware optimization techniques. Moreover, systematic studies determine optimal operating regions that optimally trade-off expressibility and noise tolerance to offer useful design advice on trusted implementation of VQAs with near-term quantum hardware.

•Jan 28, 2026•0 citations
Near-term quantum hardware offers an opportunity to augment sequence modeling, yet NISQ noise and finite-shot measurement variance often erase gains when quantum components are invoked repeatedly across long contexts. This paper proposes a Noise-Resilient Variational Quantum Transformer (VQT) that inserts shallow, connectivity-aware variational circuits selectively into transformer attention scoring, while retaining classical residual pathways for stability and scalability. The training objective is noise-aware, optimizing expected loss under sampled noise realizations, and inference applies tiered mitigation (always-on readout correction and selective zero-noise extrapolation for critical blocks). Across controlled sequence modeling and sequence-level classification evaluations, VQT improves endpoint quality and robustness under increasing noise. Relative to a parameter-matched classical transformer, the full VQT reduces perplexity from 26.8 to 24.2 (−2.6, −9.7%) and bits-per-character from 1.42 to 1.34 (−0.08), while increasing macro-F1 from 0.812 to 0.844 (+0.032, +3.9%). Calibration also improves, with ECE decreasing from 0.064 to 0.048 (−25%). Under a high-noise condition (noise strength 0.10), VQT with mitigation achieves perplexity 32.6 versus 36.2 for the classical baseline (−3.6, −9.9%) and shows a flatter degradation slope (84.0 vs 94.0) and lower robustness AUC (2.86 vs 3.04). Ablations confirm that removing noise-aware training increases the robustness penalty (Δperplexity under noise) from 8.4 to 12.1, while removing mitigation increases it to 15.3, indicating complementary contributions from optimization and mitigation. The approach remains feasible under bounded quantum cost, exemplified by 160 circuit executions per batch at 512 shots per execution.
The execution of Variational Quantum Algorithms on Noisy Intermediate-Scale Quantum hardware is severely impacted by hardware noise variations over time and decoherence. This work introduces an Adaptive Noise-Aware Variational Quantum Classifier (ANAVQC) that integrates Zero-Noise Extrapolation (ZNE) dynamically into the training loop to counter variations. The framework approximates the instantaneous depolarizing noise from calibration and adapts noise scaling and linear extrapolation to estimate noise-free expectation values at training. A two-qubit parameterized quantum circuit is built and simulated in MATLAB, with the inclusion of stochastic gradient descent coupled with parameter-shift-based gradients. The model is conditioned on a synthetic binary classification data under a time-varying depolarizing noise profile and exhibits improved convergence stability and classification accuracy over non-adaptive methods. The simulation results identify that adaptive ZNE increases model robustness against time-varying noise and offers a scalable route to reliable quantum machine learning on practical NISQ hardware. The current ANAVQC scheme is extendable to multi-qubit platforms and practical quantum backends for the purposes of future experimental testing.
The noise of quantum-enhanced learning there is a potential of quantum-enhanced learning with noisy intermediate-scale quantum (NISQ) devices, which is limited by hardware noise and finding useful circuit architectures. In this paper, a Noise-Aware Adaptive Variational Quantum Neural Network (NAVQNN) structure is proposed, which is capable of solving such issues simultaneously. The angle encoding of classical feature vectors (variance, skewness, kurtosis, entropy) of cheque images into quantum states is done on a shallow variational circuit. The noise-sensitive adaptive ansatz generator, in turn, develops the circuit layer-by-layer by picking the new parameterized gate blocks based on their validation loss with an explicit noise model and discouraging depth and two-qubit interactions in their cost functional. The ensuing variational quantum classifier is then trained by a hybrid quantum-classical optimization cycle based on the parameter-shift rule. The experiments on the UCI banknote authentication dataset indicate the usefulness of the proposed approach with the accuracy of 0.9913, precision of 0.9869, recall of 0.9934, F1-score of 0.9902, and ROC-AUC of 0.9998. Figures of prediction score densities, decision boundary, and live inference outputs are additional proof that NAVQNN can gain a strong and well-calibrated decision-making function in compliance with practical NISQ requirements. These findings suggest that noise-conscious adaptive variational circuits can be a useful foundation for quantum-enhanced financial fraud detection and various classification problems.
Variational quantum circuits (VQCs) are central to near-term quantum computing, yet their practical deployment is severely hindered by noise. While existing error mitigation methods, such as zero-noise extrapolation (ZNE), typically assume static noise, real noisy intermediate-scale quantum (NISQ) systems exhibit dynamic, time-varying noise that remains largely unaddressed. To overcome this critical gap, our work introduces a novel adaptive noise mitigation framework for VQCs that integrates ZNE with contextual multi-armed bandits (CMAB), enabling dynamic, context-aware selection of circuit-folding levels based on ansatz parameters (e.g., depth, parameter count) and the evolving noise environment. Unlike fixed-fold or heuristic ZNE, our approach uses online adaptation to improve the accuracy of ZNE and reduce redundant quantum circuit executions. Our extensive simulations and experiments on real quantum hardware reveal the following important properties: (i) deeper VQCs accumulate noise, degrading accuracy and increasing the number of quantum circuit executions; (ii) ZNE restores estimator fidelity when the folding level is chosen appropriately; and (iii) CMAB-guided folding cuts quantum circuit execution round trips by up to 40\%, bytes exchanged by up to 35\%, and end-to-end cost by up to 30\% under a 10~Mbps budget, with up to 6.9\% higher estimator fidelity (CIFAR-10, depth 3, noise band η=0.05η=0.05η=0.05), versus fixed-fold and grid-search ZNE. These results demonstrate substantial performance gains over existing noise mitigation methods, underscoring the effectiveness of our design in supporting robust noise mitigation for VQCs. The source code is also publicly released to support reproducibility.
Noise and limited circuit depth remain major obstacles for deploying quantum machine learning models on noisy intermediate-scale quantum (NISQ) devices. Variational quantum neural networks (VQNNs) are promising for near-term learning, but their performance strongly depends on ansatz design and training stability under realistic noise. In this paper, we propose a Noise-Aware Adaptive Variational Quantum Neural Network (NAVQNN) for supervised binary classification. NAVQNN combines angle-based quantum encoding with a variational classifier whose circuit structure is grown adaptively from a candidate block pool using a noise-aware selection criterion that evaluates validation loss under a depolarizing noise model and penalizes hardware cost (depth and entangling gates). The model is trained in a hybrid quantum–classical loop using parameter-shift gradients and the Adam optimizer. Experiments on the UCI Banknote Authentication dataset demonstrate strong classification performance, achieving 99.13% accuracy and AUC = 0.9998 under NISQ-like noisy simulation, with consistently high precision, recall, and F1-score. These results indicate that noise-aware adaptive circuit construction can reduce dependence on hand-crafted ansätze while maintaining reliable performance in near-term quantum learning settings.
Anomaly detection on high-dimensional tabular data requires models that are simultaneously compact, robust to noise, and interpretable, which are not met well by traditional ensemble learning approaches under strict parameter budgets. This work introduces NoiseAware-QML, a Variational Quantum Circuit (VQC) approach that incorporates a learnable noise parameterσ\sigmaσdirectly into the quantum ansatz, allowing the circuit to adaptively learn noise robustness during optimization through the reparameterization trick. The proposed 4-qubit, 4-layer VQC requires only 54 trainable parameters, a715×715 \times715×reduction over Random Forest and91×91 \times91×reduction over XGBoost, while maintaining a multi-seed mean ROC-AUC of0.8366±0.00830.8366 \pm 0.00830.8366±0.0083(95% CI: [0.8252, 0.8446]) on UNSW-NB15. Three robustness advantages with respect to parameter budget are formally established: (i) robustness to noise-1.84% AUC loss atσ=0.10\sigma=0.10σ=0.10compared to 4.12% for Random Forest (2.24× better) and 2.41% for a comparable-sized Dropout-MLP(1.31×(1.31 \times(1.31×better); (ii) calibration-ECE=0.0726\mathbf{E C E}=0.0726ECE=0.0726, improving over Random Forest (0.1127) and MLP (0.1151) by 36-37% without calibration correction; (iii) cross-dataset stability-only 5.36% AUC loss on NSL-KDD compared to 8.47% for Random Forest. Ablation study over three seeds verifies that adaptive noise regularization always improves over all variants by≈0.089\approx 0.089≈0.089AUC. Explainability through quantum-native means, per-gate gradientnorm heatmaps, and Bloch sphere analysis, demonstrates that the second-highest PCA variance component is actually harmful to anomaly detection, a result hidden from classical feature selection. Simulation-based deployment analysis confirms that the model generalizes to simulated NISQ hardware settings with AUC degradation of less than 2%.
Abstract Noisy Intermediate-Scale Quantum (NISQ) devices are near-term quantum computing devices that inherently suffer from imperfect gate implementation, decoherence, and measurement noise. The main type of variational quantum algorithms(VQAs) is based on Parameterized Quantum Circuits (PQCs), which, however, face practical challenges due to optimization instability of optimization caused by noise and reduced performance. In this paper, we suggest a comprehensive noise-resilient optimization framework for PQCs, which explicitly incorporates noise-resilient circuit architecture design, incorporating noise-aware training strategies into the variational optimization loop. The framework uses circuit structures that are efficient in depth and are hardware compatible in addition to adaptive optimizer choice, stochastic optimization, and averaging as a part of repeated measurement to reduce the impacts of realistic noise. Large-scale experiments are performed with different amounts of qubits, depths of the circuit and noise strengths with realistic noise models. The findings indicate that the convergence rate is faster, the stability is increased, the variability of run-to-run variability is minimized, and other robustness is better than the noise-unaware optimization techniques. Moreover, systematic studies determine optimal operating regions that optimally trade-off expressibility and noise tolerance to offer useful design advice on trusted implementation of VQAs with near-term quantum hardware.