Multimodal Language and Graph Learning of Adsorption Configuration in Catalysis

计算机科学 可解释性 清晰 机器学习 人工智能 图形 理论计算机科学 化学 生物化学
作者
Janghoon Ock,Rishikesh Magar,Akshay Antony,Amir Barati Farimani
出处
期刊:Cornell University - arXiv 被引量:1
标识
DOI:10.48550/arxiv.2401.07408
摘要

Adsorption energy, a reactivity descriptor, should be accurately assessed for efficient catalyst screening. This evaluation requires determining the lowest energy across various adsorption configurations on the catalytic surface. While graph neural networks (GNNs) have gained popularity as a machine learning approach for computing the energy of catalyst systems, they rely heavily on atomic spatial coordinates and often lack clarity in their interpretations. Recent advancements in language models have broadened their applicability to predicting catalytic properties, allowing us to bypass the complexities of graph representation. These models are adept at handling textual data, making it possible to incorporate observable features in a human-readable format. However, language models encounter challenges in accurately predicting the energy of adsorption configurations, typically showing a high mean absolute error (MAE) of about 0.71 eV. Our study addresses this limitation by introducing a self-supervised multi-modal learning approach, termed graph-assisted pretraining. This method significantly reduces the MAE to 0.35 eV through a combination of data augmentation, achieving comparable accuracy with DimeNet++ while using 0.4% of its training data size. Furthermore, the Transformer encoder at the core of the language model can provide insights into the feature focus through its attention scores. This analysis shows that our multimodal training effectively redirects the model's attention toward relevant adsorption configurations from adsorbate-related features, enhancing prediction accuracy and interpretability.
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
完美世界应助Ll采纳,获得10
刚刚
rubbertail完成签到,获得积分20
刚刚
黑大帅完成签到,获得积分10
刚刚
科研通AI5应助风中以菱采纳,获得10
1秒前
Lea完成签到,获得积分10
1秒前
2秒前
郑开司09发布了新的文献求助10
2秒前
minmin完成签到,获得积分10
2秒前
乐乐应助科研通管家采纳,获得10
3秒前
雪白问兰应助科研通管家采纳,获得50
3秒前
香蕉觅云应助科研通管家采纳,获得10
3秒前
难过的翎应助科研通管家采纳,获得10
3秒前
Owen应助科研通管家采纳,获得10
3秒前
彭于晏应助科研通管家采纳,获得10
3秒前
科研通AI5应助科研通管家采纳,获得10
3秒前
香蕉觅云应助科研通管家采纳,获得10
3秒前
思源应助科研通管家采纳,获得10
3秒前
Orange应助科研通管家采纳,获得10
3秒前
Hungrylunch应助科研通管家采纳,获得20
4秒前
领导范儿应助科研通管家采纳,获得10
4秒前
星辰大海应助科研通管家采纳,获得10
4秒前
prosperp应助科研通管家采纳,获得10
4秒前
传奇3应助科研通管家采纳,获得10
4秒前
4秒前
Hello应助科研通管家采纳,获得10
4秒前
orixero应助科研通管家采纳,获得10
4秒前
李爱国应助科研通管家采纳,获得10
4秒前
李健应助科研通管家采纳,获得10
4秒前
赘婿应助科研通管家采纳,获得10
4秒前
Tong完成签到,获得积分0
4秒前
Cassie应助科研通管家采纳,获得10
5秒前
充电宝应助科研通管家采纳,获得10
5秒前
搜集达人应助科研通管家采纳,获得10
5秒前
汉堡包应助科研通管家采纳,获得10
5秒前
撒啊完成签到,获得积分10
5秒前
顾矜应助科研通管家采纳,获得10
5秒前
5秒前
5秒前
小王不会看文献完成签到,获得积分10
6秒前
6秒前
高分求助中
Continuum Thermodynamics and Material Modelling 3000
Production Logging: Theoretical and Interpretive Elements 2700
Social media impact on athlete mental health: #RealityCheck 1020
Ensartinib (Ensacove) for Non-Small Cell Lung Cancer 1000
Unseen Mendieta: The Unpublished Works of Ana Mendieta 1000
Bacterial collagenases and their clinical applications 800
El viaje de una vida: Memorias de María Lecea 800
热门求助领域 (近24小时)
化学 材料科学 生物 医学 工程类 有机化学 生物化学 物理 纳米技术 计算机科学 内科学 化学工程 复合材料 基因 遗传学 物理化学 催化作用 量子力学 光电子学 冶金
热门帖子
关注 科研通微信公众号,转发送积分 3527304
求助须知:如何正确求助?哪些是违规求助? 3107454
关于积分的说明 9285518
捐赠科研通 2805269
什么是DOI,文献DOI怎么找? 1539827
邀请新用户注册赠送积分活动 716708
科研通“疑难数据库(出版商)”最低求助积分说明 709672