Optimal Transfer Learning Strategies for Property Predictions in Materials Science

财产(哲学) 计算机科学 学习迁移 数据科学 人工智能 认识论 哲学
作者
Reshma Devi,Keith T. Butler,Sai Gautam Gopalakrishnan
标识
DOI:10.1109/edtm61175.2025.11041060
摘要

Materials science is a domain characterised by ‘small’ datasets (i.e., < 10,000 datapoints) of critical properties that govern performance of various applications and devices. For instance, there are no large, reliable datasets available for several key ‘performance determining’ metrics in energy applications, such as diffusivities in battery electrodes, carrier recombination rates in photovoltaics, and molecular adsorption energies for catalysis. On the other hand, there are reasonably ‘large’ datasets (> 100,000 datapoints) available on some properties, such as, bulk formation enthalpies, computed band structures, and crystal structures across wide chemical spaces. Thus, if key chemical, compositional, and structural trends can be captured in available large datasets and subsequently transferred (or re-learnt), it will enable the use of deep learning and graph based neural network models in smaller datasets as well. Hence, my talk will explore the utility of current transfer learning (TL) approaches that are available for computational materials science and identify optimal ways to employ TL-based strategies. Specifically, TL involves training a neural network model on a larger dataset and subsequently retraining a fraction of the model on a smaller dataset. I will quantify the accuracy, transferability, and efficiency of TL models compared to models that have been trained from scratch. Finally, I will focus on TL models that can generalise over multi-properties during pre-training and can efficiently be re-trained on small datasets, which pave the way towards creating more general, foundational models, in the near future.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
cbc发布了新的文献求助10
刚刚
牛有德发布了新的文献求助10
刚刚
zhuyun_2020完成签到,获得积分10
1秒前
1秒前
Arjun发布了新的文献求助10
1秒前
1秒前
bvcw发布了新的文献求助10
1秒前
2秒前
自强不息发布了新的文献求助10
3秒前
4秒前
4秒前
能成大事发布了新的文献求助10
4秒前
肉鸡完成签到,获得积分10
5秒前
小二郎应助小鱼采纳,获得10
5秒前
老宇完成签到,获得积分10
5秒前
6秒前
6秒前
6秒前
上官若男应助qw采纳,获得10
6秒前
就睡觉啊z完成签到,获得积分10
6秒前
LB应助木玉成约采纳,获得10
6秒前
ssh发布了新的文献求助10
7秒前
bkagyin应助无言采纳,获得10
7秒前
hivivian发布了新的文献求助10
7秒前
7秒前
8秒前
8秒前
cecily发布了新的文献求助10
9秒前
9秒前
9秒前
丘比特应助闪电小子采纳,获得10
10秒前
10秒前
LYL003完成签到,获得积分10
10秒前
锂氧驳回了Hello应助
10秒前
11秒前
小郭发布了新的文献求助10
11秒前
11秒前
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Effects of Two Weeks of Red Light Therapy on Choroidal Thickness and Axial Length in Young Adults 700
Positive Art Therapy Theory and Practice 600
Management and the Arts 510
Matrix Methods in Data Mining and Pattern Recognition Second Edition 510
Key mechanistic insights into the intramolecular C-H bond amination and double bond aziridination in sulfamate esters catalyzed by dirhodium tetracarboxylate complexes 500
The Neuroscience of Language 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 工程类 有机化学 化学工程 生物化学 计算机科学 内科学 物理 复合材料 催化作用 细胞生物学 无机化学 光电子学 物理化学 电极 基因
热门帖子
关注 科研通微信公众号,转发送积分 7671253
求助须知:如何正确求助?哪些是违规求助? 9238574
关于积分的说明 19896651
捐赠科研通 7240868
什么是DOI,文献DOI怎么找? 3285035
关于科研通互助平台的介绍 2443325
邀请新用户注册赠送积分活动 2287179