BRNet: Branched Residual Network for Fast and Accurate Predictive Modeling of Materials Properties

Vishu Gupta*, Wei Keng Liao, Alok Choudhary, Ankit Agrawal

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Machine Learning (ML) and Deep Learning (DL) have become increasingly popular in the field of materials science for building property prediction models owing to their ability to efficiently extract and understand data-driven relationships between materials composition, structure, and properties. In general, materials property prediction are regression problems with a vector-based input material representation. While fully connected layers have been widely used in deep neural networks to predict materials properties, simply adding more and more layers to create a deep model often degrades their performance due to the vanishing gradient problem, thereby limiting usage. In this paper, we study and propose architectural principles for building deep regression neural networks comprising fully connected layers with numerical vectors that bypass manual feature engineering. We introduce a novel deep regression neural network with branched residual learning, BRNet, consisting of branching of layers to maximize variation of features learned from the input or previous layer and places skip connections after each layer to minimize the information loss due to vanishing gradient. We perform BRNet model training for inorganic material properties using numerical vectors representing the elemental fractions of the compositions of the respective materials and compare its performance against other traditional ML and DL techniques, including ElemNet and IRNet. Using multiple datasets (such as OQMD, MP, JARVIS) for training and testing, we show that BRNet models are significantly more accurate than the state-of-the-art ML methods and DL models for all data sizes by using only raw elemental fractions as input. We also show that BRNet’s branched residual learning requires fewer parameters and leads to better convergence during the training phase than other neural networks, thus resulting in faster model training.

Original languageEnglish (US)
Title of host publicationProceedings of the 2022 SIAM International Conference on Data Mining, SDM 2022
PublisherSociety for Industrial and Applied Mathematics Publications
Pages343-351
Number of pages9
ISBN (Electronic)9781611977172
StatePublished - 2022
Event2022 SIAM International Conference on Data Mining, SDM 2022 - Virtual, Online
Duration: Apr 28 2022Apr 30 2022

Publication series

NameProceedings of the 2022 SIAM International Conference on Data Mining, SDM 2022

Conference

Conference2022 SIAM International Conference on Data Mining, SDM 2022
CityVirtual, Online
Period4/28/224/30/22

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'BRNet: Branched Residual Network for Fast and Accurate Predictive Modeling of Materials Properties'. Together they form a unique fingerprint.

Cite this