Iterative Quantum Feature Maps

2025-06-24

AI Summary

To address circuit noise, hardware constraints, and excessive quantum resource consumption in deploying deep Quantum Feature Maps (QFMs) on near-term quantum hardware, this paper proposes a variational-parameter-free hybrid quantum-classical framework. The method iteratively stacks shallow quantum circuits with classical weight-enhancement modules, integrating contrastive learning and layer-wise training, while incorporating inter-layer classical feedback and quantum state encoding—thereby significantly reducing quantum runtime and noise sensitivity. Its core contribution lies in eliminating variational parameter optimization entirely, enabling efficient and robust deep quantum feature extraction. Experiments demonstrate that the framework outperforms Quantum Convolutional Neural Networks (QCNNs) on noisy quantum data tasks and achieves classification accuracy comparable to classical neural networks on standard image benchmarks, while drastically reducing quantum resource requirements—including qubit count, circuit depth, and measurement overhead.

Technology Category

• Machine Learning: Quantum Machine Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Quantum machine learning models that leverage quantum circuits as quantum feature maps (QFMs) are recognized for their enhanced expressive power in learning tasks. Such models have demonstrated rigorous end-to-end quantum speedups for specific families of classification problems. However, deploying deep QFMs on real quantum hardware remains challenging due to circuit noise and hardware constraints. Additionally, variational quantum algorithms often suffer from computational bottlenecks, particularly in accurate gradient estimation, which significantly increases quantum resource demands during training. We propose Iterative Quantum Feature Maps (IQFMs), a hybrid quantum-classical framework that constructs a deep architecture by iteratively connecting shallow QFMs with classically computed augmentation weights. By incorporating contrastive learning and a layer-wise training mechanism, IQFMs effectively reduces quantum runtime and mitigates noise-induced degradation. In tasks involving noisy quantum data, numerical experiments show that IQFMs outperforms quantum convolutional neural networks, without requiring the optimization of variational quantum parameters. Even for a typical classical image classification benchmark, a carefully designed IQFMs achieves performance comparable to that of classical neural networks. This framework presents a promising path to address current limitations and harness the full potential of quantum-enhanced machine learning.

Problem

• Overcoming noise and hardware limits in deep quantum feature maps
• Reducing quantum resource demands in gradient estimation
• Enhancing quantum machine learning without variational parameters

Innovation

• Hybrid quantum-classical framework with iterative shallow QFMs
• Contrastive learning and layer-wise training reduce noise
• No variational quantum parameters optimization required