Practical Quantum-Classical Feature Fusion for complex data Classification

TL;DR

This paper introduces a multimodal hybrid quantum-classical learning architecture with cross attention mid fusion, improving complex data classification by effectively integrating quantum features within classical models.

Contribution

It proposes a novel cross attention mid fusion architecture that better leverages quantum features in hybrid learning for complex, high-dimensional data.

Findings

Cross attention mid fusion improves performance on complex datasets.

Pure quantum and hybrid models underperform due to measurement loss.

Quantum features are most effective when integrated through principled fusion.

Abstract

Hybrid quantum and classical learning aims to couple quantum feature maps with the robustness of classical neural networks, yet most architectures treat the quantum circuit as an isolated feature extractor and merge its measurements with classical representations by direct concatenation. This neglects that the quantum and classical branches constitute distinct computational modalities and limits reliable performance on complex, high dimensional tabular and semi structured data, including remote sensing, environmental monitoring, and medical diagnostics. We present a multimodal formulation of hybrid learning and propose a cross attention mid fusion architecture in which a classical representation queries quantum derived feature tokens through an attention block with residual connectivity. The quantum branch is kept within practical NISQ budgets and uses up to nine qubits. We evaluate on Wine, Breast Cancer, Forest CoverType, FashionMNIST, and SteelPlatesFaults, comparing a quantum only model, a classical baseline, residual hybrid models, and the proposed mid fusion model under a consistent protocol. Pure quantum and standard hybrid designs underperform due to measurement induced information loss, while cross attention mid fusion is consistently competitive and improves performance on the more complex datasets in most cases. These findings suggest that quantum derived information becomes most valuable when integrated through principled multimodal fusion rather than used in isolation or loosely appended to classical features.