December 1 - 6, 2024
Boston, Massachusetts
Symposium Supporters
2024 MRS Fall Meeting & Exhibit
MT04.04.04

Multimodal Machine Learning for Materials Science—Composition-Structure Bimodal Learning for Experimentally Measured Properties

When and Where

Dec 3, 2024
2:30pm - 2:45pm
Hynes, Level 2, Room 210

Presenter(s)

Co-Author(s)

Sheng Gong1

Massachusetts Institute of Technology1

Abstract

Sheng Gong1

Massachusetts Institute of Technology1
The widespread application of multimodal machine learning models like GPT-4 has revolutionized various research fields including computer vision and natural language processing. However, its implementation in materials informatics remains underexplored, despite the presence of materials data across diverse modalities, such as composition and structure. The effectiveness of machine learning models trained on large calculated datasets depends on the accuracy of calculations, while experimental datasets often have limited data availability and incomplete information. This paper introduces a novel approach to multimodal machine learning in materials science via composition-structure bimodal learning. The proposed COmposition-Structure Bimodal Network (COSNet) is designed to enhance learning and predictions of experimentally measured materials properties that have incomplete structure information. Bimodal learning significantly reduces prediction errors across distinct materials properties including Li conductivity in solid electrolyte, band gap, refractive index, dielectric constant, energy, and magnetic moment, surpassing composition-only learning methods. Furthermore, we identified that data augmentation based on modal availability plays a pivotal role in the success of bimodal learning.

Symposium Organizers

Kjell Jorner, ETH Zurich
Jian Lin, University of Missouri-Columbia
Daniel Tabor, Texas A&M University
Dmitry Zubarev, IBM

Session Chairs

Kjell Jorner
Jian Lin

In this Session