Saved in:
Bibliographic Details
Main Authors: Khorana, Rahul, Noack, Marcus, Qian, Jin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15600
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913518130823168
author Khorana, Rahul
Noack, Marcus
Qian, Jin
author_facet Khorana, Rahul
Noack, Marcus
Qian, Jin
contents Developing robust representations of chemical structures that enable models to learn topological inductive biases is challenging. In this manuscript, we present a representation of atomistic systems. We begin by proving that our representation satisfies all structural, geometric, efficiency, and generalizability constraints. Afterward, we provide a general algorithm to encode any atomistic system. Finally, we report performance comparable to state-of-the-art methods on numerous tasks. We open-source all code and datasets. The code and data are available at https://github.com/rahulkhorana/PolyatomicComplexes.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15600
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Polyatomic Complexes: A topologically-informed learning representation for atomistic systems
Khorana, Rahul
Noack, Marcus
Qian, Jin
Machine Learning
Computational Physics
Developing robust representations of chemical structures that enable models to learn topological inductive biases is challenging. In this manuscript, we present a representation of atomistic systems. We begin by proving that our representation satisfies all structural, geometric, efficiency, and generalizability constraints. Afterward, we provide a general algorithm to encode any atomistic system. Finally, we report performance comparable to state-of-the-art methods on numerous tasks. We open-source all code and datasets. The code and data are available at https://github.com/rahulkhorana/PolyatomicComplexes.
title Polyatomic Complexes: A topologically-informed learning representation for atomistic systems
topic Machine Learning
Computational Physics
url https://arxiv.org/abs/2409.15600