Search Results for author: Jianjun Hu

Found 23 papers, 8 papers with code

Materials Transformers Language Models for Generative Materials Design: a benchmark study

no code implementations27 Jun 2022 Nihang Fu, Lai Wei, Yuqi Song, Qinyang Li, Rui Xin, Sadman Sadeed Omee, Rongzhi Dong, Edirisuriya M. Dilanga Siriwardane, Jianjun Hu

We also find that the properties of the generated samples can be tailored by training the models with selected training sets such as high-bandgap materials.

Natural Language Processing

Physics Guided Deep Learning for Generative Design of Crystal Materials with Symmetry Constraints

1 code implementation27 Mar 2022 Yong Zhao, Edirisuriya M. Dilanga Siriwardane, Zhenyao Wu, Nihang Fu, Mohammed Al-Fahdi, Ming Hu, Jianjun Hu

Recently, deep generative models have been proposed for generative design of materials by learning implicit knowledge from known materials datasets.

Data Augmentation Formation Energy

Semi-supervised teacher-student deep neural network for materials discovery

1 code implementation12 Dec 2021 Daniel Gleaves, Edirisuriya M. Dilanga Siriwardane, Yong Zhao, Nihang Fu, Jianjun Hu

For synthesizability prediction, our model significantly increases the baseline PU learning's true positive rate from 87. 9\% to 97. 9\% using 1/49 model parameters.

Formation Energy

Physics guided deep learning generative models for crystal materials discovery

no code implementations7 Dec 2021 Yong Zhao, Edirisuriya MD Siriwardane, Jianjun Hu

Deep learning based generative models such as deepfake have been able to generate amazing images and videos.

Data Augmentation Face Swapping

Predicting Lattice Phonon Vibrational Frequencies Using Deep Graph Neural Networks

no code implementations10 Nov 2021 Nghia Nguyen, Steph-Yves Louis, Lai Wei, Kamal Choudhary, Ming Hu, Jianjun Hu

Our work demonstrates the capability of deep graph neural networks to learn to predict phonon spectrum properties of crystal structures in addition to phonon density of states (DOS) and electronic DOS in which the output dimension is constant.

Materials Screening

Scalable deeper graph neural networks for high-performance materials property prediction

1 code implementation25 Sep 2021 Sadman Sadeed Omee, Steph-Yves Louis, Nihang Fu, Lai Wei, Sourin Dey, Rongzhi Dong, Qinyang Li, Jianjun Hu

Machine learning (ML) based materials discovery has emerged as one of the most promising approaches for breakthroughs in materials science.

Band Gap Graph Attention +1

MaterialsAtlas.org: A Materials Informatics Web App Platform for Materials Discovery and Survey of State-of-the-Art

no code implementations9 Sep 2021 Jianjun Hu, Stanislav Stefanov, Yuqi Song, Sadman Sadeed Omee, Steph-Yves Louis, Edirisuriya M. D. Siriwardane, Yong Zhao

The availability and easy access of large scale experimental and computational materials data have enabled the emergence of accelerated development of algorithms and models for materials property prediction, structure prediction, and generative design of materials.

Band Gap Materials Screening

Crystal structure prediction of materials with high symmetry using differential evolution

no code implementations20 Apr 2021 Wenhui Yang, Edirisuriya M. Dilanga Siriwardane, Rongzhi Dong, Yuxin Li, Jianjun Hu

Our experimental results show that our proposed algorithm CMCrystalHS can effectively solve the problem of inconsistent contact map dimensions and predict the crystal structures with high symmetry.

SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification

1 code implementation2 Mar 2021 Alireza Nasiri, Jianjun Hu

Our extensive benchmark experiments show that our hybrid deep network models trained with combined contrastive and cross-entropy loss achieved the state-of-the-art performance on three benchmark datasets ESC-10, ESC-50, and US8K with validation accuracies of 99. 75\%, 93. 4\%, and 86. 49\% respectively.

Contrastive Learning Data Augmentation +3

Active learning based generative design for the discovery of wide bandgap materials

2 code implementations28 Feb 2021 Rui Xin, Edirisuriya M. D. Siriwardane, Yuqi Song, Yong Zhao, Steph-Yves Louis, Alireza Nasiri, Jianjun Hu

Our experiments show that while active learning itself may sample chemically infeasible candidates, these samples help to train effective screening models for filtering out materials with desired properties from the hypothetical materials created by the generative model.

Active Learning Band Gap

NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique

1 code implementation17 Feb 2021 Steph-Yves Louis, Alireza Nasiri, Fatima J. Rolland, Cameron Mitro, Jianjun Hu

While there exists a wide variety of graph neural networks (GNN) for node classification, only a minority of them adopt mechanisms that effectively target noise propagation during the message-passing procedure.

Node Classification

AlphaCrystal: Contact map based crystal structure prediction using deep learning

no code implementations2 Feb 2021 Jianjun Hu, Yong Zhao, Wenhui Yang, Yuqi Song, Edirisuriya MD Siriwardane, Yuxin Li, Rongzhi Dong

To our knowledge, AlphaCrystal is the first neural network based algorithm for crystal structure contact map prediction and the first method for directly reconstructing crystal structures from materials composition, which can be further optimized by DFT calculations.

Protein Structure Prediction Materials Science

NODE-SELECT: A FLEXIBLE GRAPH NEURAL NETWORK BASED ON REALISTIC PROPAGATION SCHEME

no code implementations1 Jan 2021 Steph-Yves Louis, Alireza Nasiri, Fatima Christina Rolland, Cameron Mitro, Jianjun Hu

In this paper we propose the NODE-SELECT graph neural network (NSGNN): a novel and flexible graph neural network that uses subsetting filters to learn the contribution from the nodes selected to share their information.

Node Classification

Computational discovery of new 2D materials using deep learning generative models

no code implementations16 Dec 2020 Yuqi Song, Edirisuriya M. Dilanga Siriwardane, Yong Zhao, Jianjun Hu

Two dimensional (2D) materials have emerged as promising functional materials with many applications such as semiconductors and photovoltaics because of their unique optoelectronic properties.

Formation Energy

MLatticeABC: Generic Lattice Constant Prediction of Crystal Materials using Machine Learning

1 code implementation30 Oct 2020 Yuxin Li, Wenhui Yang, Rongzhi Dong, Jianjun Hu

Lattice constants such as unit cell edge lengths and plane angles are important parameters of the periodic structures of crystal materials.

Materials Science Computational Physics

A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets

no code implementations21 Jun 2020 Changchang Zeng, Shaobo Li, Qin Li, Jie Hu, Jianjun Hu

Machine Reading Comprehension (MRC) is a challenging Natural Language Processing(NLP) research field with wide real-world applications.

Machine Reading Comprehension Natural Language Processing

Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks

no code implementations17 Mar 2020 Yong Zhao, Kunpeng Yuan, Yinqiao Liu, Steph-Yves Louis, Ming Hu, Jianjun Hu

Extensive benchmark experiments over 2, 170 Fm-3m face-centered-cubic (FCC) materials show that our ECD based CNNs can achieve good performance for elasticity prediction.

Machine Learning based prediction of noncentrosymmetric crystal materials

no code implementations26 Feb 2020 Yuqi Song, Joseph Lindsay, Yong Zhao, Alireza Nasiri, Steph-Yves Louis, Jie Ling, Ming Hu, Jianjun Hu

Noncentrosymmetric materials play a critical role in many important applications such as laser technology, communication systems, quantum computing, cybersecurity, and etc.

Machine Learning

Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials

no code implementations12 Nov 2019 Yabo Dan, Yong Zhao, Xiang Li, Shaobo Li, Ming Hu, Jianjun Hu

The percentage of chemically valid (charge neutral and electronegativity balanced) samples out of all generated ones reaches 84. 5% by our GAN when trained with materials from ICSD even though no such chemical rules are explicitly enforced in our GAN model, indicating its capability to learn implicit chemical composition rules.

ComplexFace: a Multi-Representation Approach for Image Classification with Small Dataset

no code implementations21 Feb 2019 Guiying Zhang, Yuxin Cui, Yong Zhao, Jianjun Hu

State-of-the-art face recognition algorithms are able to achieve good performance when sufficient training images are provided.

Data Augmentation Face Recognition +2

A Deep Learning Algorithm for One-step Contour Aware Nuclei Segmentation of Histopathological Images

no code implementations7 Mar 2018 Yuxin Cui, Guiying Zhang, Zhonghao Liu, Zheng Xiong, Jianjun Hu

A nucleus-boundary model is introduced to predict nuclei and their boundaries simultaneously using a fully convolutional neural network.

Data Augmentation whole slide images

Cannot find the paper you are looking for? You can Submit a new open access paper.