Transfer Learning in Materials Informatics: structure-property relationships through minimal but highly informative multimodal input
In this work we propose simple, effective and computationally efficient transfer learning approaches for structure-property relation predictions in the context of materials, with highly informative input from different modalities. As materials properties stand from their electronic structure, repres...
Saved in:
Main Authors | , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
17.01.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | In this work we propose simple, effective and computationally efficient
transfer learning approaches for structure-property relation predictions in the
context of materials, with highly informative input from different modalities.
As materials properties stand from their electronic structure, representations
are extracted directly from datasets of electronic charge density profile
images using Neural Networks. We demonstrate transferability of the existing
pre-trained Convolutional Neural Networks and Large Language Models knowledge
to physics domain data, exploring a wide set of compositions for the regression
of energetics- or structure- related properties, and the role of semantic
crystallographic information in the context of multimodal approaches. We test
the applicability of the CLIP multimodal model, and employ as well a training
protocol for building a more interpretable and versatile stacked custom
solution from different pre-trained modalities. The study offers a promising
avenue for enhancing the effectiveness of descriptor identification in physical
systems, shedding light on the power of multimodal transfer learning for
materials property prediction, without any support of complex geometrical
architectures and with potential impact on decision making for new low-cost AI
methods in the field of Materials and Chemoinformatics. |
---|---|
DOI: | 10.48550/arxiv.2401.09301 |