Noisy HQNNs: A Comprehensive Analysis of Noise Robustness in Hybrid Quantum Neural Networks

TL;DR

This paper systematically analyzes the noise robustness of two hybrid quantum neural network algorithms, QCNN and QuanNN, across various noise types and levels, providing insights for improving their performance on NISQ devices.

Contribution

It offers a comprehensive comparison of QCNN and QuanNN noise resilience, highlighting how different noise channels and levels affect their performance in image classification tasks.

Findings

QuanNN is robust to low noise levels and certain noise types like bit flip at high probabilities.

QCNN can outperform noise-free models under specific high-noise conditions.

Different noise types significantly impact the performance of HQNNs, guiding future error mitigation strategies.

Abstract

Hybrid Quantum Neural Networks (HQNNs) offer promising potential of quantum computing while retaining the flexibility of classical deep learning. However, the limitations of Noisy Intermediate-Scale Quantum (NISQ) devices introduce significant challenges in achieving ideal performance due to noise interference, such as decoherence, gate errors, and readout errors. This paper presents an extensive comparative analysis of two HQNN algorithms, Quantum Convolutional Neural Network (QCNN) and Quanvolutional Neural Network (QuanNN), assessing their noise resilience across diverse image classification tasks. We systematically inject noise into variational quantum circuits using five quantum noise channels: Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and Depolarizing Noise. By varying noise probabilities from 0.1 to 1.0, we evaluate the correlation between noise robustness and model behavior across different noise levels. Our findings demonstrate that different noise types and levels significantly influence HQNN performance. The QuanNN shows robust performance across most noise channels for low noise levels (0.1 - 0.4), but succumbs to diverse effects of depolarizing and amplitude damping noise at probabilities between (0.5 - 1.0). However, the QuanNN exhibits robustness to bit flip noise at high probabilities (0.9 - 1.0). On the other hand, the QCNN tends to benefit from the noise injection by outperforming noise-free models for bit flip, phase flip, and phase damping at high noise probabilities. However, for other noise types, the QCNN shows gradual performance degradation as noise increases. These insights aim to guide future research in error mitigation strategies to enhance HQNN models in the NISQ era.