ABSTRACT
Machine Learning principles have found application to scientific domains, such as materials science, owing to their significant efficiency compared with performing ab initio calculations. In recent years, Graph Convolutional Networks (GCNs) have gained popularity in the same domain, for the task of prediction and classification of crystal properties, as they have been proven to be effective for node-representation learning while working with graph-like structures. Fundamentally, similar to conventional Convolution Neural Networks (CNNs), GCNs are also composed of convolution and pooling layers. While there is ample literature focusing on the convolution operations performed in similar models, not enough focus has been given to the pooling mechanisms employed in the same models. In this work, the proposed model employs GCNs in the domain of materials science while incorporating a relatively more sophisticated pooling mechanism that takes into account the structure of the crystals being featurized, with which we've observed better results for all the attributes tested as compared to traditional first-principles methods used for computing the same.
- Tian Xie and Jeffrey C. Grossman. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties.Physical Review Letters, 120(14), Apr 2018Google ScholarCross Ref
- Yao Ma, Suhang Wang, Charu C. Aggarwal, and Jiliang Tang. Graph convolutional networks with eigenpooling.CoRR, abs/1904.13107,2019Google Scholar
- Thomas N. Kipf and Max Welling. Semi-supervised classification with graph convolutional networks. InInternational Conference on Learning Representations (ICLR), 2017.Google Scholar
- Cheol Woo Park and Chris Wolverton. Developing an improved crystal graph convolutional neural network framework for accelerated materials discovery. Physical Review Materials, 4(6), Jun 2020.Google ScholarCross Ref
- Chi Chen, Weike Ye, Yunxing Zuo, Chen Zheng, and Shyue Ping Ong. Graph networks as a universal machine learning framework for molecules and crystals. Chemistry of Materials, 31(9):3564–3572, Apr 2019.Google ScholarCross Ref
- Kristof T. Sch ̈utt, Pieter-Jan Kindermans, Huziel E. Sauceda, Stefan Chmiela, Alexandre Tkachenko, and Klaus-Robert M ̈uller. Schnet: Acontinuous-filter convolutional neural network for modeling quantum interactions, 2017.Google Scholar
- Soumya Sanyal, Janakiraman Balachandran, Naganand Yadati, Abhishek Kumar, Padmini Rajagopalan, Suchismita Sanyal, and Partha P.Talukdar. MT-CGCNN: integrating crystal graph convolutional neuralnetwork with multitask learning for material property prediction.CoRR,abs/1811.05660, 2018Google Scholar
- Louis, Steph-Yves, Yong Zhao, Alireza Nasiri, Xiran Wang, Yuqi Song, Fei Liu, and Jianjun Hu. "Graph convolutional neural networks with global attention for improved materials property prediction." Physical Chemistry Chemical Physics 22, no. 32 (2020): 18141-18148.Google ScholarCross Ref
- Daniele Grattarola, Daniele Zambon, Filippo Maria Bianchi, and Cesare Alippi. Understanding pooling in graph neural networks, 2021.Google Scholar
- Diego Mesquita, Amauri Souza, and Samuel Kaski. Rethinking poolingin graph neural networks. In H. Larochelle, M. Ranzato, R. Hadsell,M. F. Balcan, and H. Lin, editors,Advances in Neural InformationProcessing Systems, volume 33, pages 2220–2231. Curran Associates,Inc., 202Google Scholar
- Anubhav Jain, Shyue Ping Ong, Geoffroy Hautier, Wei Chen,William Davidson Richards, Stephen Dacek, Shreyas Cholia, DanGunter, David Skinner, Gerbrand Ceder, and Kristin a. Persson. TheMaterials Project: A materials genome approach to accelerating materi-als innovation.APL Materials, 1(1):011002, 2013.Google ScholarCross Ref
Index Terms
- Prediction of Material Properties using Crystal Graph Convolutional Neural Networks
Recommendations
Exploiting node-feature bipartite graph in graph convolutional networks
AbstractIn recent years, Graph Convolutional Networks (GCNs), which extend convolutional neural networks to graph structure, have achieved great success on many graph learning tasks by fusing structure and feature information, such as node ...
A Brief Review of Receptive Fields in Graph Convolutional Networks
WI '19 Companion: IEEE/WIC/ACM International Conference on Web Intelligence - Companion VolumeConvolutional neural networks have been shown successful in extracting features from images and texts. However, it is difficult to apply convolutional neural networks directly on ubiquitous graph data since the graph data lies in an irregular structure. ...
Graph Convolutional Neural Networks for Web-Scale Recommender Systems
KDD '18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningRecent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of ...
Comments