The role of data embedding in equivariant quantum convolutional neural networks

Abstract

Geometric deep learning refers to the scenario in which the symmetries of a dataset are used to constrain the parameter space of a neural network and thus, improve their trainability and generalization. Recently this idea has been incorporated into the field of quantum machine learning, which has given rise to equivariant quantum neural networks (EQNNs). In this work, we investigate the role of classical-to-quantum embedding on the performance of equivariant quantum convolutional neural networks (EQCNNs) for the classification of images. We discuss the connection between the data embedding method and the resulting representation of a symmetry group and analyze how changing representation affects the expressibility of an EQCNN. We numerically compare the classification accuracy of EQCNNs with three different basis-permuted amplitude embeddings to the one obtained from a non-equivariant quantum convolutional neural network (QCNN). Our results show a clear dependence of classification accuracy on the underlying embedding, especially for initial training iterations. The improvement in classification accuracy of EQCNN over non-equivariant QCNN may be present or absent depending on the particular embedding and dataset used. It is expected that the results of this work can be useful to the community for a better understanding of the importance of data embedding choice in the context of geometric quantum machine learning.

arXiv comment12 pages, 9 figures. Significant changes compared to previous version. New results added

References in corpus (50)

• Deep Learning in Neural Networks: An Overview
• Quantum Computing in the NISQ era and beyond
• Supplementary information for "Quantum supremacy using a programmable superconducting processor"
• Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer
• Quantum Machine Learning
• A variational eigenvalue solver on a quantum processor
• Barren plateaus in quantum neural network training landscapes
• The theory of variational hybrid quantum-classical algorithms
• Quantum support vector machine for big data classification
• Quantum Circuit Learning
• Quantum Convolutional Neural Networks
• An introduction to quantum machine learning
• Parameterized quantum circuits as machine learning models
• Cost Function Dependent Barren Plateaus in Shallow Parametrized Quantum Circuits
• Circuit-centric quantum classifiers
• Expressibility and entangling capability of parameterized quantum circuits for hybrid quantum-classical algorithms
• A class of quantum many-body states that can be efficiently simulated
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Quantum advantage in learning from experiments
• A rigorous and robust quantum speed-up in supervised machine learning
• Quantum autoencoders for efficient compression of quantum data
• Generalization in quantum machine learning from few training data
• Quantum convolutional neural network for classical data classification
• Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
• Provably efficient machine learning for quantum many-body problems
• Is quantum advantage the right goal for quantum machine learning?
• Exploiting symmetry in variational quantum machine learning
• Group-Invariant Quantum Machine Learning
• Hybrid Quantum-Classical Generative Adversarial Network for High Resolution Image Generation
• Asymptotic Improvements to Quantum Circuits via Qutrits
• Approximate amplitude encoding in shallow parameterized quantum circuits and its application to financial market indicator
• Theory for Equivariant Quantum Neural Networks
• Theoretical Guarantees for Permutation-Equivariant Quantum Neural Networks
• Restrictions on realizable unitary operations imposed by symmetry and locality
• Generative quantum machine learning via denoising diffusion probabilistic models
• Speeding up Learning Quantum States through Group Equivariant Convolutional Quantum Ansätze
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification
• Provably Trainable Rotationally Equivariant Quantum Machine Learning
• Model-Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
• Quantum-Noise-Driven Generative Diffusion Models
• Quantum Reinforcement Learning: the Maze problem
• Experimental quantum pattern recognition in IBMQ and diamond NVs
• Symmetry breaking in geometric quantum machine learning in the presence of noise
• Deep learning enhanced noise spectroscopy of a spin qubit environment
• Approximately Equivariant Quantum Neural Network for $p4m$ Group Symmetries in Images
• How to enhance quantum generative adversarial learning of noisy information
• A hybrid-qudit representation of digital RGB images
• Machine learning classification of non-Markovian noise disturbing quantum dynamics
• Machine-learning based noise characterization and correction on neutral atoms NISQ devices
• Permutation-equivariant quantum convolutional neural networks

Cited by in corpus (2)

• Barren Plateaus in Variational Quantum Computing
• Permutation-equivariant quantum convolutional neural networks