通过自适应剪枝降低量子神经网络的数据复杂度，提升效率与鲁棒性。
ATP: Adaptive Threshold Pruning for Efficient Data Encoding in Quantum Neural Networks
- 根据动态阈值剪除数据中非关键特征，降低量子电路需求。
- 实验证明可减少纠缠熵并提升对抗训练下的鲁棒性。
- 适合资源受限的量子计算场景，兼顾性能与效率。
量子神经网络（QNNs）在处理复杂数据任务方面具有潜力，但常受制于有限的量子比特资源和高纠缠度，影响可扩展性和效率。本文提出自适应阈值剪枝（ATP），一种用于降低数据复杂度、减少纠缠的编码方法。ATP基于自适应阈值动态剪除数据中的非必要特征，有效降低量子电路需求的同时保持高性能。在多个数据集上的大量实验表明，结合对抗训练方法（如FGSM）时，ATP能显著降低纠缠熵并增强对抗鲁棒性。结果表明，ATP可在计算效率与模型韧性之间取得良好平衡，在资源受限条件下实现显著性能提升，使QNNs在实际应用中更具可行性。
原文摘要 · Abstract (English)
Quantum Neural Networks (QNNs) offer promising capabilities for complex data tasks, but are often constrained by limited qubit resources and high entanglement, which can hinder scalability and efficiency. In this paper, we introduce Adaptive Threshold Pruning (ATP), an encoding method that reduces entanglement and optimizes data complexity for efficient computations in QNNs. ATP dynamically prunes non-essential features in the data based on adaptive thresholds, effectively reducing quantum circuit requirements while preserving high performance. Extensive experiments across multiple datasets demonstrate that ATP reduces entanglement entropy and improves adversarial robustness when combined with adversarial training methods like FGSM. Our results highlight ATPs ability to balance computational efficiency and model resilience, achieving significant performance improvements with fewer resources, which will help make QNNs more feasible in practical, resource-constrained settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。