PERM EQ x GRAPH EQ: Equivariant Neural Networks for Quantum Molecular Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Biswas, Saumya, Oswal, Jiten
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911304124465152
author Biswas, Saumya
Oswal, Jiten
author_facet Biswas, Saumya
Oswal, Jiten
contents In hierarchal order of molecular geometry, we compare the performances of Geometric Quantum Machine Learning models. Two molecular datasets are considered: the simplistic linear shaped LiH-molecule and the trigonal pyramidal molecule NH3. Both accuracy and generalizability metrics are considered. A classical equivariant model is used as a baseline for the performance comparison. The comparative performance of Quantum Machine Learning models with no symmetry equivariance, rotational and permutational equivariance, and graph embedded permutational equivariance is investigated. The performance differentials and the molecular geometry in question reveals the criteria for choice of models for generalizability. Graph embedding of features is shown to be an effective pathway to greater trainability for geometric datasets. Permutational symmetric embedding is found to be the most generalizable quantum Machine Learning model for geometric learning.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05475
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PERM EQ x GRAPH EQ: Equivariant Neural Networks for Quantum Molecular Learning
Biswas, Saumya
Oswal, Jiten
Machine Learning
Artificial Intelligence
Quantum Physics
68T05, 68T09, 81P68
F.2.2; I.2.6; I.2.7
In hierarchal order of molecular geometry, we compare the performances of Geometric Quantum Machine Learning models. Two molecular datasets are considered: the simplistic linear shaped LiH-molecule and the trigonal pyramidal molecule NH3. Both accuracy and generalizability metrics are considered. A classical equivariant model is used as a baseline for the performance comparison. The comparative performance of Quantum Machine Learning models with no symmetry equivariance, rotational and permutational equivariance, and graph embedded permutational equivariance is investigated. The performance differentials and the molecular geometry in question reveals the criteria for choice of models for generalizability. Graph embedding of features is shown to be an effective pathway to greater trainability for geometric datasets. Permutational symmetric embedding is found to be the most generalizable quantum Machine Learning model for geometric learning.
title PERM EQ x GRAPH EQ: Equivariant Neural Networks for Quantum Molecular Learning
topic Machine Learning
Artificial Intelligence
Quantum Physics
68T05, 68T09, 81P68
F.2.2; I.2.6; I.2.7
url https://arxiv.org/abs/2512.05475