ResQuNNs: Towards Enabling Deep Learning in Quantum Convolution Neural Networks

TL;DR

This paper introduces ResQuNNs, a novel architecture that incorporates residual learning into quantum convolutional neural networks, enabling trainable layers and improved gradient flow for better training and performance.

Contribution

The paper proposes a new residual architecture for quantum CNNs that allows training of multiple trainable quanvolutional layers, overcoming gradient flow challenges.

Findings

Residual blocks improve gradient access across layers.

Optimal placement of residual blocks enhances training efficiency.

ResQuNNs outperform static quanvolutional networks in experiments.

Abstract

In this paper, we present a novel framework for enhancing the performance of Quanvolutional Neural Networks (QuNNs) by introducing trainable quanvolutional layers and addressing the critical challenges associated with them. Traditional quanvolutional layers, although beneficial for feature extraction, have largely been static, offering limited adaptability. Unlike state-of-the-art, our research overcomes this limitation by enabling training within these layers, significantly increasing the flexibility and potential of QuNNs. However, the introduction of multiple trainable quanvolutional layers induces complexities in gradient-based optimization, primarily due to the difficulty in accessing gradients across these layers. To resolve this, we propose a novel architecture, Residual Quanvolutional Neural Networks (ResQuNNs), leveraging the concept of residual learning, which facilitates the flow of gradients by adding skip connections between layers. By inserting residual blocks between quanvolutional layers, we ensure enhanced gradient access throughout the network, leading to improved training performance. Moreover, we provide empirical evidence on the strategic placement of these residual blocks within QuNNs. Through extensive experimentation, we identify an efficient configuration of residual blocks, which enables gradients across all the layers in the network that eventually results in efficient training. Our findings suggest that the precise location of residual blocks plays a crucial role in maximizing the performance gains in QuNNs. Our results mark a substantial step forward in the evolution of quantum deep learning, offering new avenues for both theoretical development and practical quantum computing applications.