Practical Quantum-Classical Feature Fusion for complex data Classification

2025-12-22

AI Summary

Quantum-classical hybrid models for high-dimensional tabular and semi-structured data classification (e.g., remote sensing, medical diagnosis) suffer from modality fragmentation and information loss due to naive concatenative fusion. Method: We propose a cross-modal middle-fusion architecture where classical representations serve as queries, and residual cross-attention dynamically attends to quantum feature tokens—enabling structured, bidirectional collaboration between quantum and classical branches. Contribution/Results: We introduce the first quantum-classical cross-attention middle-fusion paradigm, explicitly designed for NISQ constraints (≤9 qubits) and robust against measurement-induced representation degradation. Evaluated on benchmarks including Forest CoverType and SteelPlatesFaults, our method significantly outperforms pure quantum, concatenative hybrid, and classical baselines, demonstrating both semantic alignment across modalities and robust collaborative gains.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

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.

Problem

• Fuses quantum and classical features for complex data classification
• Addresses limitations of isolated quantum feature extraction in hybrid models
• Enhances performance on high-dimensional tabular and semi-structured datasets

Innovation

• Cross attention mid fusion architecture
• Quantum branch within NISQ budgets
• Multimodal integration of quantum and classical features