[论文解读] RoQNN: Noise-Aware Training for Robust Quantum Neural Networks.

Hanrui Wang, Jiaqi Gu+5 more|arXiv (Cornell University)|Oct 21, 2021

Quantum Computing Algorithms and Architecture参考文献 59被引用 6

一句话总结

RoQNN 是一种针对噪声近场量子硬件的噪声感知训练框架，可提升量子神经网络（QNNs）的鲁棒性。它通过测量后归一化、基于真实硬件噪声模型的训练期间噪声注入，以及测量后量化来缓解噪声影响，在真实量子设备上实现高达43%的准确率提升，并在2分类MNIST分类任务中达到94%以上的准确率。

ABSTRACT

Quantum Neural Network (QNN) is a promising application towards quantum advantage on near-term quantum hardware. However, due to the large quantum noises (errors), the performance of QNN models has a severe degradation on real quantum devices. For example, the accuracy gap between noise-free simulation and noisy results on IBMQ-Yorktown for MNIST-4 classification is over 60%. Existing noise mitigation methods are general ones without leveraging unique characteristics of QNN and are only applicable to inference; on the other hand, existing QNN work does not consider noise effect. To this end, we present RoQNN, a QNN-specific framework to perform noise-aware optimizations in both training and inference stages to improve robustness. We analytically deduct and experimentally observe that the effect of quantum noise to QNN measurement outcome is a linear map from noise-free outcome with a scaling and a shift factor. Motivated by that, we propose post-measurement normalization to mitigate the feature distribution differences between noise-free and noisy scenarios. Furthermore, to improve the robustness against noise, we propose noise injection to the training process by inserting quantum error gates to QNN according to realistic noise models of quantum hardware. Finally, post-measurement quantization is introduced to quantize the measurement outcomes to discrete values, achieving the denoising effect. Extensive experiments on 8 classification tasks using 6 quantum devices demonstrate that RoQNN improves accuracy by up to 43%, and achieves over 94% 2-class, 80% 4-class, and 34% 10-class MNIST classification accuracy measured on real quantum computers. We also open-source our PyTorch library for construction and noise-aware training of QNN at this https URL .

研究动机与目标

• 解决QNN在噪声近场量子硬件上出现的严重性能下降问题。
• 克服通用噪声缓解方法的局限性，后者仅适用于推理阶段，且未利用QNN特有的特性。
• 开发一种训练时框架，主动提升QNN对量子噪声的鲁棒性。
• 弥合标准基准任务中无噪声仿真与真实设备结果之间的准确率差距。

提出的方法

• 分析推导并实验验证：量子噪声会对无噪声QNN测量结果产生线性变换（缩放与偏移）。
• 应用测量后归一化，通过校正缩放与偏移因子，使无噪声与噪声场景下的特征分布对齐。
• 基于硬件特定的噪声模型，将真实的量子错误门注入QNN训练过程，以模拟并适应实际噪声。
• 引入测量后量化，对测量结果进行离散化处理，降低对噪声的敏感性，增强鲁棒性。
• 将归一化、噪声注入与量化整合为统一的训练流水线，实现端到端的噪声感知优化。

实验结果

研究问题

• RQ1 量子噪声对QNN测量结果的影响能否建模为线性变换？该建模是否可用于噪声缓解？
• RQ2 在QNN训练中使用真实硬件噪声模型进行噪声注入，在提升鲁棒性方面效果如何？
• RQ3 测量后归一化是否能有效减少无噪声与噪声推理结果之间的分布偏移？
• RQ4 测量后量化在真实量子设备上对提升QNN准确率的改善程度如何？
• RQ5 归一化、噪声注入与量化三者联合对多样化分类任务中QNN性能的影响如何？

主要发现

• RoQNN 在8个分类任务中，使真实量子硬件上的QNN准确率最高提升43%。
• 在IBMQ-Yorktown设备上，RoQNN在2分类MNIST分类任务中准确率超过94%，显著缩小了标准QNN中60%以上的准确率差距。
• 在4分类MNIST分类任务中，RoQNN在真实量子设备上实现了超过80%的准确率。
• 在10分类MNIST分类任务中，RoQNN在真实硬件上达到34%的准确率，证明了其在多分类任务中的可行性。
• 该框架的各组成部分——测量后归一化、噪声注入与量化——协同作用，使QNN在6种不同量子设备上均表现出鲁棒性能。