Saved in:
Bibliographic Details
Main Authors: Spellings, Matthew, Martirossyan, Maya, Dshemuchadse, Julia
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.14680
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910708513374208
author Spellings, Matthew
Martirossyan, Maya
Dshemuchadse, Julia
author_facet Spellings, Matthew
Martirossyan, Maya
Dshemuchadse, Julia
contents Recent work has proven that training large language models with self-supervised tasks and fine-tuning these models to complete new tasks in a transfer learning setting is a powerful idea, enabling the creation of models with many parameters, even with little labeled data; however, the number of domains that have harnessed these advancements has been limited. In this work, we formulate a set of geometric tasks suitable for the large-scale study of ordered three-dimensional structures, without requiring any human intervention in data labeling. We build deep rotation- and permutation-equivariant neural networks based on geometric algebra and use them to solve these tasks on both idealized and simulated three-dimensional structures. Quantifying order in complex-structured assemblies remains a long-standing challenge in materials physics; these models can elucidate the behavior of real self-assembling systems in a variety of ways, from distilling insights from learned tasks without further modification to solving new tasks with smaller amounts of labeled data via transfer learning.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14680
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Supervised Learning for Ordered Three-Dimensional Structures
Spellings, Matthew
Martirossyan, Maya
Dshemuchadse, Julia
Machine Learning
Recent work has proven that training large language models with self-supervised tasks and fine-tuning these models to complete new tasks in a transfer learning setting is a powerful idea, enabling the creation of models with many parameters, even with little labeled data; however, the number of domains that have harnessed these advancements has been limited. In this work, we formulate a set of geometric tasks suitable for the large-scale study of ordered three-dimensional structures, without requiring any human intervention in data labeling. We build deep rotation- and permutation-equivariant neural networks based on geometric algebra and use them to solve these tasks on both idealized and simulated three-dimensional structures. Quantifying order in complex-structured assemblies remains a long-standing challenge in materials physics; these models can elucidate the behavior of real self-assembling systems in a variety of ways, from distilling insights from learned tasks without further modification to solving new tasks with smaller amounts of labeled data via transfer learning.
title Self-Supervised Learning for Ordered Three-Dimensional Structures
topic Machine Learning
url https://arxiv.org/abs/2411.14680