QSTAR: Quantum Selective Transfer with Adaptive Routing

• URL: http://arxiv.org/abs/2607.21411v1
• Date: Thu, 23 Jul 2026 15:14:29 GMT
• Title: QSTAR: Quantum Selective Transfer with Adaptive Routing
• Abstract summary: We propose a selective QTL framework that routes only low-confidence samples to a fallback branch.<n>We compare manually designed QTL heads, KetGPT-designed quantum heads, and parameter-matched classical baselines.<n> Adaptive KetGPT-QTL reaches 80.9% accuracy and 0.807 F1-score, outperforming the adaptive classical baseline.
• Score: 2.417944170423441
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum transfer learning (QTL) is often evaluated by replacing a classical classifier with a fixed variational quantum head, but this hides a key question: when is the quantum branch actually useful? We propose QSTAR: Quantum Selective Transfer with Adaptive Routing, a selective QTL framework that keeps high-confidence classical predictions and routes only low-confidence samples to a fallback branch. Using a frozen ResNet18 backbone on Fashion-MNIST, we compare manually designed QTL heads, KetGPT-designed quantum heads, and parameter-matched classical baselines under a common data split and optimization schedule. Standard QTL heads reach at most 57.0% accuracy, while the strongest KetGPT head in the main filtered sweep reaches 78.5% accuracy and 0.785 F1-score. Although the strongest fixed classical head remains higher at 81.6%, selective routing gives the quantum branch a clearer role. On low-confidence samples, KetGPT #180 improves accuracy over a parameter-matched MLP fallback by 6.82, 4.31, and 3.03 percentage points at thresholds of 0.70, 0.80, and 0.90. At the full-system level, Adaptive KetGPT-QTL reaches 80.9% accuracy and 0.807 F1-score, outperforming the adaptive classical baseline. A separate compact-circuit ablation identifies KetGPT #160 as a stronger fixed-head candidate, reaching 81.9% accuracy with only 10 quantum parameters and 9 gates. These results suggest that architecture-searched quantum heads are most useful as targeted fallback branches for uncertain inputs rather than uniform replacements for classical classifiers.

Related papers

• Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement [0.05999777817331314]
  We evaluate a 10-qubit hybrid quantum-classical variational circuit for paraphrase detection.<n>On QQP the circuit achieves 75.53% +/- 0.75% accuracy.<n>On MRPC the optimal 2-layer variant reaches 92% of BERT-base accuracy at 54,000 lower parameter cost.<n>These results constitute the first systematic parameter-matched multi-benchmark empirical validation of hybrid variational circuits for NLP.
  arXiv  Detail & Related papers  (2026-09-13T14:06:49Z)
• Quantum Feature Engineering for Credit Default Prediction: When and Why IQP Circuits Help Linear Classifiers [3.029054495277686]
  We show that IQP circuits can produce features that improve a classifier over both its raw classical baseline and Kernel PCA.<n>We also show that how the 8 input features are chosen matters; Random Forest importance-guided selection reaches F1 = 0.523, while encoding maximally uncorrelated features drops it to 0.496.
  arXiv  Detail & Related papers  (2026-09-09T17:41:27Z)
• Classical and Hybrid Quantum Machine Learning for Trigger-Like Event Selection on CMS Open Data: An Eight-Qubit, PCA-Constrained Benchmark [0.9106818059692908]
  Event triggering sits at the heart of high-energy physics, where rare events of interest must be retained.<n>This work compares four classical machine learning models, namely a support vector machine, an artificial neural network, a convolutional network and a long short-term memory network.<n>Four hybrid quantum counterparts, on a trigger-like binary classification task built from CMS open data.
  arXiv  Detail & Related papers  (2026-08-26T15:32:44Z)
• QuantumPhaseNet: A Gauge-Covariant Geometric and Quantum-Spectral Theory of Semantic Concept Hierarchies with Prototype Validation of a Classical Quantum-Inspired Model [0.0]
  We present QuantumPhaseNet, a quantum-spectral extension of Transformer representations.<n> Context-dependent semantic states are modeled as complex amplitudes.<n>Low-frequency graph modes define a document-level discourse direction.
  arXiv  Detail & Related papers  (2026-08-16T15:52:50Z)
• OQMD: Single-Qubit Rotation Control Improves Low-CNOT Multiclass Quantum Classification [4.669017653337737]
  This work studies Optimal Quantum Measurement Decoding (OQMD)<n>OQMD: optimizing how quantum outcomes are mapped to classical labels by training a readout layer before measurement.<n>Experiments use trainable triple single-qubit rotations as one concrete, hardware-native realization of OQMD.
  arXiv  Detail & Related papers  (2026-06-12T04:05:48Z)
• QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation [2.417944170423441]
  Scene Graph Generation (SGG) requires relational reasoning over objects and their interactions.<n> classical SGG models frequently rely on dataset statistics, leading to biased predictions toward frequent relations.<n>This work introduces a hybrid quantum predicate classifier for SGG by replacing the classical predicate head in Causal Feature Enhancement Network (CFEN) with a Quantum Predicate Head (QP-Head) trained using weighted cross-entropy.
  arXiv  Detail & Related papers  (2026-06-03T10:15:56Z)
• Gated QKAN-FWP: Scalable Quantum-inspired Sequence Learning [38.502127166117674]
  We propose gated QKAN-FWP, a fast-weight framework that integrates FWP with Quantum-inspired Kolmogorov-Arnold Network (QKAN)<n>We use single-qubit data re-uploading circuits as learnable nonlinear activation, known as DatA Re-Uploading ActivatioN (DARUAN)<n>We evaluate the framework across time-series benchmarks, MiniGrid reinforcement learning, and highlight real-world solar cycle forecasting as our main practical result.
  arXiv  Detail & Related papers  (2026-05-07T13:04:09Z)
• QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation [39.32132630606808]
  We introduce QuanBench+, a unified benchmark spanning Qiskit, PennyLane, and Cirq.<n>We evaluate models with executable functional tests, report Pass@1 and Pass@5, and use KL-divergence-based acceptance for probabilistic outputs.<n>Across frameworks, the strongest one-shot scores reach 59.5% in Qiskit, 54.8% in Cirq, and 42.9% in PennyLane.
  arXiv  Detail & Related papers  (2026-03-25T20:51:21Z)
• Hybrid Quantum-Classical Optimisation of Traveling Salesperson Problem [0.0]
  We propose a hybrid quantum-classical framework integrating variational quantum eigensolver (VQE) optimisation with classical machine learning.<n>We evaluate the framework on 80 European cities via Qiskit's AerSimulator and ibm_kyiv 127-qubit backend.
  arXiv  Detail & Related papers  (2025-09-30T13:26:12Z)
• Benchmarking Classical and Quantum Models for DeFi Yield Prediction on Curve Finance [0.0]
  We benchmark six models, XGBoost, Random Forest, LSTM, Transformer, quantum neural networks (QNN), and quantum support vector machines with quantum feature maps (QSVM-QNN)<n>We evaluate model performance on test MAE, RMSE, and directional accuracy.<n>XGBoost achieves the highest directional accuracy (71.57%) with a test MAE of 1.80, while Random Forest attains the lowest test MAE of 1.77 and 71.36% accuracy.
  arXiv  Detail & Related papers  (2025-07-22T06:55:20Z)
• GroverGPT: A Large Language Model with 8 Billion Parameters for Quantum Searching [43.496857395654764]
  We explore the potential of leveraging Large Language Models to simulate the output of a quantum Turing machine.<n>A specialized model, GroverGPT, trained on over 15 trillion tokens.<n>It consistently outperformed OpenAI's GPT-4o (45% accuracy), achieving nearly 100% accuracy on 6- and 10-qubit datasets.<n>It also demonstrated strong generalization, surpassing 95% accuracy for systems with over 20 qubits when trained on 3- to 6-qubit data.
  arXiv  Detail & Related papers  (2024-12-30T20:23:10Z)
• On the Convergence of DP-SGD with Adaptive Clipping [56.24689348875711]
  Gradient Descent with gradient clipping is a powerful technique for enabling differentially private optimization.<n>This paper provides the first comprehensive convergence analysis of SGD with quantile clipping (QC-SGD)<n>We show how QC-SGD suffers from a bias problem similar to constant-threshold clipped SGD but can be mitigated through a carefully designed quantile and step size schedule.
  arXiv  Detail & Related papers  (2024-12-27T20:29:47Z)
• Tensor Ring Optimized Quantum-Enhanced Tensor Neural Networks [32.76948546010625]
  Quantum machine learning researchers often rely on incorporating Networks (TN) into Deep Neural Networks (DNN) To address this issue, a multi-layer design of a Ring optimized variational Quantum learning classifier (Quan-TR) is proposed. It is referred to as Ring optimized Quantum-enhanced neural Networks (TR-QNet) On quantum simulations, the proposed TR-QNet achieves promising accuracy of $94.5%$, $86.16%$, and $83.54%$ on the Iris, MNIST, and CIFAR-10 datasets, respectively.
  arXiv  Detail & Related papers  (2023-10-02T18:07:10Z)
• Direct pulse-level compilation of arbitrary quantum logic gates on superconducting qutrits [36.30869856057226]
  We demonstrate any arbitrary qubit and qutrit gate can be realized with high-fidelity, which can significantly reduce the length of a gate sequence. We show that optimal control gates are robust to drift for at least three hours and that the same calibration parameters can be used for all implemented gates.
  arXiv  Detail & Related papers  (2023-03-07T22:15:43Z)
• CAFQA: A classical simulation bootstrap for variational quantum algorithms [8.659073885003684]
  The CAFQA ansatz is a hardware-efficient circuit built with only Clifford gates. CAFQA achieves mean accuracy improvements of 6.4x and 56.8x, over the state-of-the-art, on different metrics. With CAFQA's high-accuracy, the convergence of VQAs is shown to accelerate by 2.5x, even for small molecules.
  arXiv  Detail & Related papers  (2022-02-25T19:29:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.