Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yan, Keqiang, Bohde, Montgomery, Kryvenko, Andrii, Xiang, Ziyu, Zhao, Kaiji, Zhu, Siya, Kolachina, Saagar, Sarıtürk, Doğuhan, Xie, Jianwen, Arroyave, Raymundo, Qian, Xiaoning, Qian, Xiaofeng, Ji, Shuiwang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.05771
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915312923836416
author Yan, Keqiang
Bohde, Montgomery
Kryvenko, Andrii
Xiang, Ziyu
Zhao, Kaiji
Zhu, Siya
Kolachina, Saagar
Sarıtürk, Doğuhan
Xie, Jianwen
Arroyave, Raymundo
Qian, Xiaoning
Qian, Xiaofeng
Ji, Shuiwang
author_facet Yan, Keqiang
Bohde, Montgomery
Kryvenko, Andrii
Xiang, Ziyu
Zhao, Kaiji
Zhu, Siya
Kolachina, Saagar
Sarıtürk, Doğuhan
Xie, Jianwen
Arroyave, Raymundo
Qian, Xiaoning
Qian, Xiaofeng
Ji, Shuiwang
contents Machine learning interatomic potentials (MLIPs) can predict energy, force, and stress of materials and enable a wide range of downstream discovery tasks. A key design choice in MLIPs involves the trade-off between invariant and equivariant architectures. Invariant models offer computational efficiency but may not perform as well, especially when predicting high-order outputs. In contrast, equivariant models can capture high-order symmetries, but are computationally expensive. In this work, we propose HIENet, a hybrid invariant-equivariant materials interatomic potential model that integrates both invariant and equivariant message passing layers, while provably satisfying key physical constraints. HIENet achieves state-of-the-art performance with considerable computational speedups over prior models. Experimental results on both common benchmarks and downstream materials discovery tasks demonstrate the efficiency and effectiveness of HIENet.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05771
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures
Yan, Keqiang
Bohde, Montgomery
Kryvenko, Andrii
Xiang, Ziyu
Zhao, Kaiji
Zhu, Siya
Kolachina, Saagar
Sarıtürk, Doğuhan
Xie, Jianwen
Arroyave, Raymundo
Qian, Xiaoning
Qian, Xiaofeng
Ji, Shuiwang
Machine Learning
Materials Science
Computational Physics
Machine learning interatomic potentials (MLIPs) can predict energy, force, and stress of materials and enable a wide range of downstream discovery tasks. A key design choice in MLIPs involves the trade-off between invariant and equivariant architectures. Invariant models offer computational efficiency but may not perform as well, especially when predicting high-order outputs. In contrast, equivariant models can capture high-order symmetries, but are computationally expensive. In this work, we propose HIENet, a hybrid invariant-equivariant materials interatomic potential model that integrates both invariant and equivariant message passing layers, while provably satisfying key physical constraints. HIENet achieves state-of-the-art performance with considerable computational speedups over prior models. Experimental results on both common benchmarks and downstream materials discovery tasks demonstrate the efficiency and effectiveness of HIENet.
title A Materials Foundation Model via Hybrid Invariant-Equivariant Architectures
topic Machine Learning
Materials Science
Computational Physics
url https://arxiv.org/abs/2503.05771