Multi-Class Quantum Convolutional Neural Networks

TL;DR

This paper introduces a quantum convolutional neural network (QCNN) for multi-class classification of classical data, demonstrating competitive performance with classical CNNs on the MNIST dataset, especially as the number of classes increases.

Contribution

The work presents a novel QCNN architecture for multi-class classification implemented with PennyLane, highlighting its advantages over classical CNNs in higher-class scenarios.

Findings

QCNN outperforms classical CNN with more classes

Performance is slightly lower than classical CNN with 4 classes

Demonstrates feasibility of quantum models for image classification

Abstract

Classification is particularly relevant to Information Retrieval, as it is used in various subtasks of the search pipeline. In this work, we propose a quantum convolutional neural network (QCNN) for multi-class classification of classical data. The model is implemented using PennyLane. The optimization process is conducted by minimizing the cross-entropy loss through parameterized quantum circuit optimization. The QCNN is tested on the MNIST dataset with 4, 6, 8 and 10 classes. The results show that with 4 classes, the performance is slightly lower compared to the classical CNN, while with a higher number of classes, the QCNN outperforms the classical neural network.