Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ko, Tsz Wai, Deng, Bowen, Nassar, Marcel, Barroso-Luque, Luis, Liu, Runze, Qi, Ji, Liu, Elliott, Ceder, Gerbrand, Miret, Santiago, Ong, Shyue Ping
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910859941380096
author Ko, Tsz Wai
Deng, Bowen
Nassar, Marcel
Barroso-Luque, Luis
Liu, Runze
Qi, Ji
Liu, Elliott
Ceder, Gerbrand
Miret, Santiago
Ong, Shyue Ping
author_facet Ko, Tsz Wai
Deng, Bowen
Nassar, Marcel
Barroso-Luque, Luis
Liu, Runze
Qi, Ji
Liu, Elliott
Ceder, Gerbrand
Miret, Santiago
Ong, Shyue Ping
contents Graph deep learning models, which incorporate a natural inductive bias for a collection of atoms, are of immense interest in materials science and chemistry. Here, we introduce the Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry. Built on top of the popular Deep Graph Library (DGL) and Python Materials Genomics (Pymatgen) packages, our intention is for MatGL to be an extensible ``batteries-included'' library for the development of advanced graph deep learning models for materials property predictions and interatomic potentials. At present, MatGL has efficient implementations for both invariant and equivariant graph deep learning models, including the Materials 3-body Graph Network (M3GNet), MatErials Graph Network (MEGNet), Crystal Hamiltonian Graph Network (CHGNet), TensorNet and SO3Net architectures. MatGL also includes a variety of pre-trained universal interatomic potentials (aka ``foundational materials models (FMM)'') and property prediction models are also included for out-of-box usage, benchmarking and fine-tuning. Finally, MatGL includes support for Pytorch Lightning for rapid training of models.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03837
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry
Ko, Tsz Wai
Deng, Bowen
Nassar, Marcel
Barroso-Luque, Luis
Liu, Runze
Qi, Ji
Liu, Elliott
Ceder, Gerbrand
Miret, Santiago
Ong, Shyue Ping
Materials Science
Chemical Physics
Graph deep learning models, which incorporate a natural inductive bias for a collection of atoms, are of immense interest in materials science and chemistry. Here, we introduce the Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry. Built on top of the popular Deep Graph Library (DGL) and Python Materials Genomics (Pymatgen) packages, our intention is for MatGL to be an extensible ``batteries-included'' library for the development of advanced graph deep learning models for materials property predictions and interatomic potentials. At present, MatGL has efficient implementations for both invariant and equivariant graph deep learning models, including the Materials 3-body Graph Network (M3GNet), MatErials Graph Network (MEGNet), Crystal Hamiltonian Graph Network (CHGNet), TensorNet and SO3Net architectures. MatGL also includes a variety of pre-trained universal interatomic potentials (aka ``foundational materials models (FMM)'') and property prediction models are also included for out-of-box usage, benchmarking and fine-tuning. Finally, MatGL includes support for Pytorch Lightning for rapid training of models.
title Materials Graph Library (MatGL), an open-source graph deep learning library for materials science and chemistry
topic Materials Science
Chemical Physics
url https://arxiv.org/abs/2503.03837