Enregistré dans:
Détails bibliographiques
Auteurs principaux: Oyama, Yosuke, Majima, Yusuke, Ohta, Eiji, Sakai, Yasufumi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.22208
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915309896597504
author Oyama, Yosuke
Majima, Yusuke
Ohta, Eiji
Sakai, Yasufumi
author_facet Oyama, Yosuke
Majima, Yusuke
Ohta, Eiji
Sakai, Yasufumi
contents Neural network potentials (NNPs) are crucial for accelerating computational materials science by surrogating density functional theory (DFT) calculations. Improving their accuracy is possible through pre-training and fine-tuning, where an NNP model is first pre-trained on a large-scale dataset and then fine-tuned on a smaller target dataset. However, this approach is computationally expensive, mainly due to the cost of DFT-based dataset labeling and load imbalances during large-scale pre-training. To address this, we propose LaMM, a semi-supervised pre-training method incorporating improved denoising self-supervised learning and a load-balancing algorithm for efficient multi-node training. We demonstrate that our approach effectively leverages a large-scale dataset of $\sim$300 million semi-labeled samples to train a single NNP model, resulting in improved fine-tuning performance in terms of both speed and accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LaMM: Semi-Supervised Pre-Training of Large-Scale Materials Models
Oyama, Yosuke
Majima, Yusuke
Ohta, Eiji
Sakai, Yasufumi
Machine Learning
Neural network potentials (NNPs) are crucial for accelerating computational materials science by surrogating density functional theory (DFT) calculations. Improving their accuracy is possible through pre-training and fine-tuning, where an NNP model is first pre-trained on a large-scale dataset and then fine-tuned on a smaller target dataset. However, this approach is computationally expensive, mainly due to the cost of DFT-based dataset labeling and load imbalances during large-scale pre-training. To address this, we propose LaMM, a semi-supervised pre-training method incorporating improved denoising self-supervised learning and a load-balancing algorithm for efficient multi-node training. We demonstrate that our approach effectively leverages a large-scale dataset of $\sim$300 million semi-labeled samples to train a single NNP model, resulting in improved fine-tuning performance in terms of both speed and accuracy.
title LaMM: Semi-Supervised Pre-Training of Large-Scale Materials Models
topic Machine Learning
url https://arxiv.org/abs/2505.22208