QuIC provides a training-free quantum graph embedding proven permutation-invariant and injective for labeled graphs under an irrational-angle condition in the ideal case, with empirical separation shown on noisy hardware for hard graph families including CFI instances.
Supervised learning with quantum- enhanced feature spaces
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
An adaptive shot-allocation rule that spends noisy kernel-estimation measurements on SVM decision-critical entries beats uniform allocation and can stop early.
Simulated fidelity quantum kernels achieve competitive or better accuracy than RBF kernels on Indian Pines binary and multiclass tasks and Methane Detection data without heavy dimensionality reduction.
Quantum reservoir computing with distributed architectures reduces time-series forecasting errors by up to 78.8% MAE and 72.3% RMSE in NISQ simulations compared to classical methods.
QPINN combines quantum feature mapping via Nyström method with physics-informed constraints to achieve 99.46% average SOH estimation accuracy on a 310k-sample multi-chemistry battery dataset, outperforming baselines by up to 65% in MAPE.
A quantum-assisted SVM ensemble using annealing achieves IoU of 0.60 and balanced accuracy of 0.89 on Sentinel-1 oil spill imagery, comparable to classical baselines and generalizing to independent Strait of Hormuz data.
A parameter-matched hybrid QCNN fusing classical features with amplitude-encoding and angle-encoding 4-qubit VQCs achieves statistically significant accuracy gains over a classical CNN on BreastMNIST (Wilcoxon p=0.03125, Cohen's d=2.14).
Two neural network architectures achieve state-of-the-art performance in quantum state tomography for pure and mixed states by incorporating class information.
citing papers explorer
-
QuIC: A Training-Free Quantum Graph Embedding from Ideal Analysis to Practical Hardware Evaluation
QuIC provides a training-free quantum graph embedding proven permutation-invariant and injective for labeled graphs under an irrational-angle condition in the ideal case, with empirical separation shown on noisy hardware for hard graph families including CFI instances.
-
Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations
An adaptive shot-allocation rule that spends noisy kernel-estimation measurements on SVM decision-critical entries beats uniform allocation and can stop early.
-
Large-Scale Quantum Kernels for Hyperspectral Data Classification
Simulated fidelity quantum kernels achieve competitive or better accuracy than RBF kernels on Indian Pines binary and multiclass tasks and Methane Detection data without heavy dimensionality reduction.
-
Scalable Quantum Reservoir Computing over Distributed Quantum Architectures
Quantum reservoir computing with distributed architectures reduces time-series forecasting errors by up to 78.8% MAE and 72.3% RMSE in NISQ simulations compared to classical methods.
-
Battery health prognosis using Physics-informed neural network with Quantum Feature mapping
QPINN combines quantum feature mapping via Nyström method with physics-informed constraints to achieve 99.46% average SOH estimation accuracy on a 310k-sample multi-chemistry battery dataset, outperforming baselines by up to 65% in MAPE.
-
Toward Near-Real-Time Marine Oil Spill Detection in SAR Imagery using Quantum-Assisted SVM
A quantum-assisted SVM ensemble using annealing achieves IoU of 0.60 and balanced accuracy of 0.89 on Sentinel-1 oil spill imagery, comparable to classical baselines and generalizing to independent Strait of Hormuz data.
-
Parallel Multi-Circuit Quantum Feature Fusion in Hybrid Quantum-Classical Convolutional Neural Networks for Breast Tumor Classification
A parameter-matched hybrid QCNN fusing classical features with amplitude-encoding and angle-encoding 4-qubit VQCs achieves statistically significant accuracy gains over a classical CNN on BreastMNIST (Wilcoxon p=0.03125, Cohen's d=2.14).
-
Optical Quantum Mixed-State Reconstruction With Multiple Deep Learning Approaches
Two neural network architectures achieve state-of-the-art performance in quantum state tomography for pure and mixed states by incorporating class information.