CLAQS: Compact Learnable All-Quantum Token Mixer with Shared-ansatz for Text Classification

• URL: http://arxiv.org/abs/2510.06532v1
• Date: Wed, 08 Oct 2025 00:20:08 GMT
• Title: CLAQS: Compact Learnable All-Quantum Token Mixer with Shared-ansatz for Text Classification
• Abstract summary: We present CLAQS, a compact, fully quantum token mixer for text classification.<n>We apply l1 normalization to regulate amplitude scaling and introduce a two-stage parameterized quantum architecture.<n> operating under a sliding-window regime, CLAQS requires only eight data qubits and shallow circuits, yet achieves 91.64% accuracy on SST-2 and 87.08% on IMDB.
• Score: 25.923244871975058
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum compute is scaling fast, from cloud QPUs to high throughput GPU simulators, making it timely to prototype quantum NLP beyond toy tasks. However, devices remain qubit limited and depth limited, training can be unstable, and classical attention is compute and memory heavy. This motivates compact, phase aware quantum token mixers that stabilize amplitudes and scale to long sequences. We present CLAQS, a compact, fully quantum token mixer for text classification that jointly learns complex-valued mixing and nonlinear transformations within a unified quantum circuit. To enable stable end-to-end optimization, we apply l1 normalization to regulate amplitude scaling and introduce a two-stage parameterized quantum architecture that decouples shared token embeddings from a window-level quantum feed-forward module. Operating under a sliding-window regime with document-level aggregation, CLAQS requires only eight data qubits and shallow circuits, yet achieves 91.64% accuracy on SST-2 and 87.08% on IMDB, outperforming both classical Transformer baselines and strong hybrid quantum-classical counterparts.

Related papers

• Quantum Incremental Learning with Mixed State Prototypes [53.319426778720434]
  We introduce a novel quantum incremental learning framework based on trainable mixed-state prototypes.<n>Our model achieves high-dimensional feature concentration using a minimal number of qubits.
  arXiv  Detail & Related papers  (2026-08-11T04:22:42Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Readout-Side Bypass for Residual Hybrid Quantum-Classical Models [3.609274776085931]
  Quantum machine learning (QML) promises compact and expressive representations, but suffers from measurement bottleneck.<n>We propose a lightweight residual hybrid architecture that confirms quantum features with raw inputs before classification.<n>Our model achieves up to +55% accuracy improvement over quantum baselines, while retaining low communication cost and enhanced privacy robustness.
  arXiv  Detail & Related papers  (2025-11-25T23:27:53Z)
• Quantum Machine Learning for Predicting Binding Free Energies in Structure-Based Virtual Screening [0.0]
  We introduce a quantum machine learning approach that encodes molecular information into quantum states.<n>With six quantum circuit units, the model achieves an RMSD of 2.37 kcal/mol and a Pearson correlation of 0.650.
  arXiv  Detail & Related papers  (2025-07-24T14:01:39Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [60.996803677584424]
  Variational Quantum Circuits (VQCs) offer a novel pathway for quantum machine learning.<n>Their practical application is hindered by inherent limitations such as constrained linear expressivity, optimization challenges, and acute sensitivity to quantum hardware noise.<n>This work introduces VQC-MLPNet, a scalable and robust hybrid quantum-classical architecture designed to overcome these obstacles.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Quantum autoencoders for image classification [0.0]
  Quantum autoencoders (QAEs) leverage classical optimization solely for parameter tuning.<n>This study introduces a novel image-classification approach using QAEs, achieving classification without requiring additional qubits.
  arXiv  Detail & Related papers  (2025-02-21T07:13:38Z)
• 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)
• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [62.46800898243033]
  Recent progress in quantum learning theory prompts a question: can linear properties of a large-qubit circuit be efficiently learned from measurement data generated by varying classical inputs?<n>We prove that the sample complexity scaling linearly in $d$ is required to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d.<n>We propose a kernel-based method leveraging classical shadows and truncated trigonometric expansions, enabling a controllable trade-off between prediction accuracy and computational overhead.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity [50.387179833629254]
  We introduce a collaborative classical-quantum architecture called co-TenQu. Co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. It outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.
  arXiv  Detail & Related papers  (2024-02-23T14:09:41Z)
• QuantumSEA: In-Time Sparse Exploration for Noise Adaptive Quantum Circuits [82.50620782471485]
  QuantumSEA is an in-time sparse exploration for noise-adaptive quantum circuits. It aims to achieve two key objectives: (1) implicit circuits capacity during training and (2) noise robustness. Our method establishes state-of-the-art results with only half the number of quantum gates and 2x time saving of circuit executions.
  arXiv  Detail & Related papers  (2024-01-10T22:33:00Z)
• On-the-fly Tailoring towards a Rational Ansatz Design for Digital Quantum Simulations [0.0]
  It is imperative to develop low depth quantum circuits that are physically realizable in quantum devices. We develop a disentangled ansatz construction protocol that can dynamically tailor an optimal ansatz. The construction of the ansatz may potentially be performed in parallel quantum architecture through energy sorting and operator commutativity prescreening.
  arXiv  Detail & Related papers  (2023-02-07T11:22:01Z)
• Reducing Unitary Coupled Cluster Circuit Depth by Classical Stochastic Amplitude Pre-Screening [0.0]
  Unitary Coupled Cluster (UCC) approaches are an appealing route to utilising quantum hardware to perform quantum chemistry calculations. We present a combined classical-quantum approach where a classical UCC pre-processing step is used to determine the important excitations in the UCC ansatz.
  arXiv  Detail & Related papers  (2021-08-24T18:34:14Z)

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.