Enforcing exact permutation and rotational symmetries in the application of quantum neural network on point cloud datasets

2024/05/18 by Z. Li, Lento Nagano, Li, Zhelun +3 · 1 citation
Engineering · #FOS: Physical sciences #High Energy Physics - Experiment (hep-ex) #Optical Systems and Laser Technology #Quantum Physics (quant-ph)

paper · pdf · doi:10.48550/arxiv.2405.11150

openalex publication_date 2024/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent developments in the field of quantum machine learning have promoted the idea of incorporating physical symmetries in the structure of quantum circuits. A crucial milestone in this area is the realization of S_n-permutation equivariant quantum neural networks (QNN) that are equivariant under permutations of input objects. In this work, we focus on encoding the rotational symmetry of point cloud datasets into the QNN. The key insight of the approach is that all rotationally invariant functions with vector inputs are equivalent to a function with inputs of vector inner products. We provide a novel structure of QNN that is exactly invariant to both rotations and permutations, with its efficacy demonstrated numerically in the problems of two-dimensional image classifications and identifying high-energy particle decays, produced by proton-proton collisions, with the SO(1,3) Lorentz symmetry.

Cited by

• Data for Towards Improved Quantum Machine Learning for Molecular Force Fields

Related

• Solving graph problems using permutation-invariant quantum machine learning
• A regularization method for quantum neural networks using data symmetry
• Resource-efficient equivariant quantum convolutional neural networks
• PERM EQ x GRAPH EQ: Equivariant Neural Networks for Quantum Molecular Learning
• Training Classical Neural Networks by Quantum Machine Learning