PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Classification

• URL: http://arxiv.org/abs/2607.13466v1
• Date: Wed, 15 Jul 2026 05:53:58 GMT
• Title: PQFA: Parallel Quantum Feature Augmentation of Fused Representations for Multimodal Classification
• Abstract summary: We propose Parallel Quantum Feature Augmentation (PQFA), a hybrid quantum-classical framework that applies multiple shallow variational quantum circuits to fused multimodal features.<n>We evaluate PQFA on MM-IMDb and N24-News through controlled comparisons using the same encoders, fusion backbone, data splits, projection dimension, and augmentation parameters.
• Score: 2.920575300184085
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most multimodal learning methods improve how heterogeneous representations are aligned and fused, while post-fusion enhancement remains less explored. We propose Parallel Quantum Feature Augmentation (PQFA), a hybrid quantum-classical framework that applies multiple shallow variational quantum circuits to fused multimodal features. Text and image representations extracted by frozen RoBERTa and ViT encoders are processed through bidirectional cross-attention, attentive pooling, and adaptive gated fusion. The fused feature is then amplitude-encoded into parallel quantum circuits, whose measurement readouts are concatenated with the classical representation for prediction. We evaluate PQFA on MM-IMDb and N24News through controlled comparisons using the same encoders, fusion backbone, data splits, projection dimension, and augmentation output width. PQFA consistently outperforms both the fusion backbone without quantum augmentation and a width-matched MLP augmentation baseline, while using approximately 2.2K augmentation parameters compared with 24.0K for the MLP branch. Missing-modality experiments further show improved robustness when textual or visual inputs are incomplete, with particularly clear gains when the more informative textual modality is severely degraded. Controlled ablations and feature-space analyses indicate that the improvement cannot be reproduced by random feature mappings, increased classical width, or untrained quantum transformations. Quantum-state diagnostics additionally show stable predictive performance across the tested simulated noise levels and distinct branch-specific transformations of the encoded states. These results establish PQFA as an effective and parameter-efficient strategy for post-fusion augmentation in hybrid quantum-classical multimodal learning.

Related papers

• A Quantum-Classical Hybrid Framework for Multivariate Time-Series Forecasting Complexity-Fidelity Trade-offs and Limitations [4.77829808535938]
  This paper introduces two model variants Quantum Reservoir Forecaster (QRC-F) and Variational Quantum Forecaster (VQF-F)<n>The proposed framework investigates the complexity-fidelity trade-off of quantum forecasting under near-term NISQ hardware constraints.<n>Results establish a practical quantum-native forecasting framework with strong potential for deployment on near-term NISQ devices.
  arXiv  Detail & Related papers  (2026-07-17T10:30:12Z)
• Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models [46.61944018676346]
  We propose a training-free token pruning framework based on Cross-Layer Spectral Evolution (CLSE)<n>Instead of measuring token importance from single-layer feature magnitudes, CLSE quantifies how token representations evolve across Transformer layers in the frequency domain.<n>CLSE achieves a superior trade-off between efficiency and accuracy under aggressive token reduction.
  arXiv  Detail & Related papers  (2026-06-23T05:39:52Z)
• BARFI-Q: Quantum-Enhanced Block Attention Residual Fusion Framework for Multivariate Time-Series Forecasting in Atom Interferometry [3.2350449526046567]
  This paper proposes a Quantum-Enhanced Block Attention Residual Fusion framework for time-series forecasting in atom interferometry.<n>BarFI-Q integrates patch-based embedding, dual-branch temporal modeling, hierarchical fusion, adaptive block-attention residual aggregation, and a quantum feature-mapping module.<n>Results indicate that multiscale temporal learning, hierarchical fusion, adaptive residual routing, and quantum-enhanced latent transformation provide an effective framework for atom-interferometric time-series forecasting.
  arXiv  Detail & Related papers  (2026-05-06T19:26:56Z)
• On the Complementarity of Quantum and Classical Features: Adaptive Hybrid Quantum-Classical Feature Fusion for Breast Cancer Classification [1.4856472820492366]
  The integration of quantum machine learning with classical deep learning offers promising avenues for medical image analysis.<n>We propose a novel hybrid quantum-classical architecture for breast cancer diagnosis based on a dual-branch feature-extraction pipeline.<n>Our framework extracts and unifies complementary representations from classical models and quantum circuits.
  arXiv  Detail & Related papers  (2026-04-24T14:54:53Z)
• Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction [45.25461515976432]
  Plug-and-Play diffusion prior (DP) frameworks have emerged as a powerful paradigm for imaging reconstruction.<n>We present a novel approach to resolving bias-hallucination trade-off, achieving state-of-the-art gradients with significantly accelerated convergence.
  arXiv  Detail & Related papers  (2026-02-26T16:58:43Z)
• Spectral Phase Encoding for Quantum Kernel Methods [0.0]
  We analyze how quantum feature constructions degrade under controlled additive noise estimation.<n>We introduce Spectral Phase.<n>SPE, a hybrid construc- tion combining a discrete Fourier transform (DFT) front-end with a diagonal phase-only embedding aligned with the geometry of diagonal quantum maps.
  arXiv  Detail & Related papers  (2026-02-23T09:42:42Z)
• 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)
• Expressive and Scalable Quantum Fusion for Multimodal Learning [16.82193084379014]
  The proposed method, called the Quantum Fusion Layer (QFL), replaces classical fusion schemes with a hybrid quantum-classical procedure.<n>In simulation, QFL consistently outperforms strong classical baselines on small but diverse multimodal tasks.<n>These results suggest that QFL offers a fundamentally new and scalable approach to multimodal fusion that merits deeper exploration on larger systems.
  arXiv  Detail & Related papers  (2025-10-08T12:19:44Z)
• Quantum Approximate Optimization Algorithm for MIMO with Quantized b-bit Beamforming [47.98440449939344]
  Multiple-input multiple-output (MIMO) is critical for 6G communication, offering improved spectral efficiency and reliability.<n>This paper explores the use of the Quantum Approximate Optimization Algorithm (QAOA) and alternating optimization to address the problem of b-bit quantized phase shifters both at the transmitter and the receiver.<n>We demonstrate that the structure of this quantized beamforming problem aligns naturally with hybrid-classical methods like QAOA, as the phase shifts used in beamforming can be directly mapped to rotation gates in a quantum circuit.
  arXiv  Detail & Related papers  (2025-10-07T17:53:02Z)
• Quantum Flow Matching [7.246258513838036]
  Quantum Flow Matching offers efficient between two density matrices.<n>QFM can be realized on quantum computers without the need for costly circuit redesigns.<n>These results position QFM as a unifying and promising framework for generative modeling across quantum systems.
  arXiv  Detail & Related papers  (2025-08-17T16:00:20Z)
• PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification [49.37555541088792]
  Phase-Amplitude Decoupling (PAD) is a frequency-aware framework that separates phase (modality-shared) and amplitude (modality-complementary) components.<n>This work establishes a new paradigm for physics-aware multi-modal fusion in remote sensing.
  arXiv  Detail & Related papers  (2025-04-27T07:21:42Z)
• Towards Efficient Quantum Hybrid Diffusion Models [68.43405413443175]
  We propose a new methodology to design quantum hybrid diffusion models. We propose two possible hybridization schemes combining quantum computing's superior generalization with classical networks' modularity.
  arXiv  Detail & Related papers  (2024-02-25T16:57:51Z)

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.