Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification

• URL: http://arxiv.org/abs/2608.06846v1
• Date: Fri, 07 Aug 2026 06:09:28 GMT
• Title: Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification
• Abstract summary: We test whether a parameterized quantum circuit (PQC) improves a hybrid quantum-classical model's performance on classical datasets.<n>Our architecture, Quantum-Embedded Attention (QEA), uses a learnable projector to compress backbone features into an $n_q$-dimensional angle vector.<n>We report all planned canonical runs, distinguish current Pauli-readout results from legacy probability-readout experiments, and analyze bottleneck, simulation, finite-shot, and noise limitations.
• Score: 1.472161528588343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We test whether a parameterized quantum circuit (PQC) improves a hybrid quantum-classical model's performance on classical datasets, using an interface-matched classical map as the control while holding all other components fixed. Our architecture, Quantum-Embedded Attention (QEA), uses a learnable projector to compress backbone features into an $n_q$-dimensional angle vector, a shallow PQC to map those angles to one- and two-qubit Pauli expectations, and a classical attention decoder to produce class logits. We hypothesized the PQC would improve accuracy or seed-to-seed stability over a classical map with matched input/output dimensions. We test this with an interface-matched $2\times2$ factorial on Breast Cancer Wisconsin at $n_q\in\{4,8\}$, independently swapping the PQC for a classical map and the attention decoder for a linear head, across five paired seeds per cell. Three of four paired quantum-minus-classical $95\%$ confidence intervals include zero; the fourth, a $+1.63$ percentage-point contrast for the attention decoder at $n_q=4$, reverses sign at $n_q=8$ and does not survive correction across the four contrasts. The experiment thus shows no consistent PQC contribution and cannot establish equivalence. A five-dataset cross-modality grid shows comparable accuracy on AG~News, Breast Cancer Wisconsin, and BirdCLEF but a large deficit on CIFAR-10; these cells are not interface-matched and are interpreted descriptively. We report all planned canonical runs, distinguish current Pauli-readout results from legacy probability-readout experiments, and analyze bottleneck, simulation, finite-shot, and noise limitations. The results do not establish a quantum advantage; they demonstrate why controlled component attribution is necessary before crediting a hybrid model's performance to its quantum layer.

Related papers

• 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)
• Predicting Multipartite Entanglement in Quantum Circuits using Transformer [0.11242503819703259]
  Multipartite entanglement is a critical property of parameterized quantum circuits (PQCs)<n>We introduce a graph-based transformer surrogate that predicts both the first-order Meyer-Wallach measure ($Q$) and the second-order Scott measure ($Q$)<n>Our central contribution is the qubit-interconnected graph (QIG) encoding for transformers, where each node represents a qubit and weighted adjacencies record entangling-gate multiplicities.
  arXiv  Detail & Related papers  (2026-08-28T07:00:20Z)
• The Fourier Wall: Why Public Tabular Datasets Refuse Quantum Advantage, and a Certified Recipe for Where It Lives [0.0]
  Quantum machine-learning models usually lose to carefully tuned classical baselines.<n>We operationalize the conditions as SPECTRA, a simulator-free structural screen.<n>On industrial smart-meter data, SPECTRA correctly refuses the real peak-load target, for which gradient-boosted trees reach a held-out ROC-AUC of 0.999.
  arXiv  Detail & Related papers  (2026-07-17T10:24:57Z)
• Active Quantum Kernel Acquisition for Gaussian Process Regression [30.032230630492155]
  Recent work on quantum kernel classification has shown that allocating shots non-uniformly across kernel entries can reduce the shot budget required to reach a target accuracy.<n>We extend this idea to Gaussian process (GP) regression, a setting whose downstream quantities (full-spectrum posterior variance, log-determinant, marginal likelihood) couple to kernel error more tightly than the sign-only outputs of classification.<n>We derive three closed-form pair-level sensitivities predictive coupling $|_i_j|$, leave-one-out residual, and marginal-likelihood gradient and plug them into a Neyman-style minimum
  arXiv  Detail & Related papers  (2026-06-27T09:40:20Z)
• Do Quantum Transformers Help? A Systematic VQC Architecture Comparison on Tabular Benchmarks [2.005299372367689]
  Variational quantum circuits (VQCs) are a leading approach to quantum machine learning on near-term devices.<n>We compare four VQC families -- multi-layer fully-connected (FC-VQC), residual (ResNet-VQC), hybrid quantum-classical transformer (QT), and fully quantum transformer (FQT)<n>FC-VQCs achieve 90-96% of the $R2$ of attention-based VQCs while using 40-50% fewer parameters.<n>These findings provide practical architectural guidance for deploying VQCs on near-term quantum hardware.
  arXiv  Detail & Related papers  (2026-04-27T01:13:14Z)
• Fixed-Reservoir vs Variational Quantum Architectures for Chaotic Dynamics: Benchmarking QRC and QPINN on the Lorenz System [0.14323566945483496]
  We compare two quantum approaches for chaotic time-series prediction on the Lorenz system.<n>We formalize a temporal windowing technique within the QRC pipeline that improves attractor reconstruction.<n>Our findings suggest the fixed-reservoir architecture is a primary driver of QRC's advantage at these scales.
  arXiv  Detail & Related papers  (2026-04-26T14:43:03Z)
• Large-scale portfolio optimization on a trapped-ion quantum computer [32.24411362086563]
  We present an end-to-end pipeline for large-scale portfolio selection with cardinality constraints.<n>We experimentally demonstrate it on trapped-ion quantum processors using hardware-aware decomposition.
  arXiv  Detail & Related papers  (2026-02-27T12:36:14Z)
• Shallow IQP circuit and graph generation [37.067444579637076]
  We introduce shallow instantaneous quantum-time circuits as generative graph models.<n>We study bipartite and ErdHos-R'enyi distributions through simulations and large-scale experiments.
  arXiv  Detail & Related papers  (2025-11-07T14:28:56Z)
• Analog Quantum Feature Selection with Neutral-Atom Quantum Processors [31.458406135473805]
  We present a quantum-native approach to quantum feature selection (QFS) based on analog quantum simulation with neutral atom arrays.<n>The protocol is evaluated through simulations on three benchmark binary classification datasets: Adult Income, Bank Marketing, and Telco Churn.<n>For compact subsets of 2-5 features, analog QFS improves mean AUC scores by 1.5-2.3% while reducing the number of features by 75-84%.
  arXiv  Detail & Related papers  (2025-10-23T17:57:34Z)
• Extending Quantum Perceptrons: Rydberg Devices, Multi-Class Classification, and Error Tolerance [67.77677387243135]
  Quantum Neuromorphic Computing (QNC) merges quantum computation with neural computation to create scalable, noise-resilient algorithms for quantum machine learning (QML) At the core of QNC is the quantum perceptron (QP), which leverages the analog dynamics of interacting qubits to enable universal quantum computation.
  arXiv  Detail & Related papers  (2024-11-13T23:56:20Z)
• Evaluating Ground State Energies of Chemical Systems with Low-Depth Quantum Circuits and High Accuracy [6.81054341190257]
  We develop an enhanced Variational Quantum Eigensolver (VQE) ansatz based on the Qubit Coupled Cluster (QCC) approach. We evaluate our enhanced QCC ansatz on two distinct quantum hardware, IBM Kolkata and Quantinuum H1-1.
  arXiv  Detail & Related papers  (2024-02-21T17:45:03Z)
• Quantum Symmetric Private Information Retrieval with Secure Storage and Eavesdroppers [32.97918488607827]
  We consider both the classical and quantum variations of $X$-secure, $E$-eavesdropped and $T$-colluding symmetric private information retrieval (SPIR) We first develop a scheme for classical $X$-secure, $E$-eavesdropped and $T$-colluding SPIR (XSETSPIR) based on a modified version of cross subspace alignment (CSA)
  arXiv  Detail & Related papers  (2023-08-21T17:30:38Z)
• Realization of arbitrary doubly-controlled quantum phase gates [62.997667081978825]
  We introduce a high-fidelity gate set inspired by a proposal for near-term quantum advantage in optimization problems. By orchestrating coherent, multi-level control over three transmon qutrits, we synthesize a family of deterministic, continuous-angle quantum phase gates acting in the natural three-qubit computational basis.
  arXiv  Detail & Related papers  (2021-08-03T17:49:09Z)

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.