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

• URL: http://arxiv.org/abs/2103.00608v1
• Date: Sun, 28 Feb 2021 20:15:23 GMT
• Title: Active learning based generative design for the discovery of wide bandgap materials
• Authors: Rui Xin, Edirisuriya M. D. Siriwardane, Yuqi Song, Yong Zhao, Steph-Yves Louis, Alireza Nasiri, Jianjun Hu
• Abstract summary: We present an active generative inverse design method that combines active learning with a deep variational autoencoder neural network and a generative adversarial deep neural network model. The application of this method has allowed us to discover new thermodynamically stable materials with high band gap and semiconductors with specified band gap ranges. 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.
• Score: 6.5175897155391755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Active learning has been increasingly applied to screening functional materials from existing materials databases with desired properties. However, the number of known materials deposited in the popular materials databases such as ICSD and Materials Project is extremely limited and consists of just a tiny portion of the vast chemical design space. Herein we present an active generative inverse design method that combines active learning with a deep variational autoencoder neural network and a generative adversarial deep neural network model to discover new materials with a target property in the whole chemical design space. The application of this method has allowed us to discover new thermodynamically stable materials with high band gap (SrYF$_5$) and semiconductors with specified band gap ranges (SrClF$_3$, CaClF$_5$, YCl$_3$, SrC$_2$F$_3$, AlSCl, As$_2$O$_3$), all of which are verified by the first principle DFT calculations. 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. The experiments show the effectiveness of our active generative inverse design approach.

Related papers

• MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning [16.48834281521776]
  Multi-Fidelity Latent space Active Learning (MF-LAL) is a generative modeling framework that integrates a set of oracles with varying cost-accuracy tradeoffs. We show that MF-LAL produces compounds with significantly better binding free energy scores than other single and multi-fidelity approaches.
  arXiv  Detail & Related papers  (2024-10-15T03:15:05Z)
• Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features [115.33889811527533]
  Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks.
  arXiv  Detail & Related papers  (2024-10-04T16:05:14Z)
• Molecule Design by Latent Prompt Transformer [76.2112075557233]
  This work explores the challenging problem of molecule design by framing it as a conditional generative modeling task. We propose a novel generative model comprising three components: (1) a latent vector with a learnable prior distribution; (2) a molecule generation model based on a causal Transformer, which uses the latent vector as a prompt; and (3) a property prediction model that predicts a molecule's target properties and/or constraint values using the latent prompt.
  arXiv  Detail & Related papers  (2024-02-27T03:33:23Z)
• Data Distillation for Neural Network Potentials toward Foundational Dataset [6.373914211316965]
  generative models can swiftly propose promising materials for targeted applications. However, the predicted properties of materials through the generative models often do not match with calculated properties through ab initio calculations. This study utilized extended ensemble molecular dynamics (MD) to secure a broad range of liquid- and solid-phase configurations in one of the metallic systems, nickel. We found that the NNP trained from the distilled data could predict different energy-minimized closed-pack crystal structures even though those structures were not explicitly part of the initial data.
  arXiv  Detail & Related papers  (2023-11-09T14:41:45Z)
• Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction [121.97742787439546]
  How to accurately predict the properties of molecules is an essential problem in AI-driven drug discovery. To reduce annotation cost, deep Active Learning methods are developed to select only the most representative and informative data for annotating. We propose a Task-type-generic active learning framework (termed Tyger) that is able to handle different types of learning tasks in a unified manner.
  arXiv  Detail & Related papers  (2022-05-23T12:56:12Z)
• Benchmarking Active Learning Strategies for Materials Optimization and Discovery [17.8738267360992]
  We present a reference dataset to benchmark active learning strategies in the form of various acquisition functions. We discuss the relationship between algorithm performance, materials search space, complexity, and the incorporation of prior knowledge.
  arXiv  Detail & Related papers  (2022-04-12T14:27:33Z)
• Semi-supervised teacher-student deep neural network for materials discovery [6.333015476935593]
  We propose a semi-supervised deep neural network (TSDNN) model for high-performance formation energy and synthesizability prediction. For formation energy based stability screening, our model achieves an absolute 10.3% accuracy improvement compared to the baseline CGCNN regression model. 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.
  arXiv  Detail & Related papers  (2021-12-12T04:00:21Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)
• Deep Bayesian Active Learning for Accelerating Stochastic Simulation [74.58219903138301]
  Interactive Neural Process (INP) is a deep active learning framework for simulations and with active learning approaches. For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models. The results demonstrate STNP outperforms the baselines in the learning setting and LIG achieves the state-of-the-art for active learning.
  arXiv  Detail & Related papers  (2021-06-05T01:31:51Z)
• Interpretable discovery of new semiconductors with machine learning [10.09604500193621]
  We report an evolutionary algorithm powered search which uses machine-learned surrogate models trained on hybrid functional DFT data benchmarked against experimental bandgaps: Deep Adaptive Regressive Weighted Intelligent Network (DARWIN) The strategy enables efficient search over the materials space of 10$8$ ternaries and 10$11$ quaternaries$7$ for candidates with target properties.
  arXiv  Detail & Related papers  (2021-01-12T10:23:16Z)
• Ensemble Transfer Learning for the Prediction of Anti-Cancer Drug Response [49.86828302591469]
  In this paper, we apply transfer learning to the prediction of anti-cancer drug response. We apply the classic transfer learning framework that trains a prediction model on the source dataset and refines it on the target dataset. The ensemble transfer learning pipeline is implemented using LightGBM and two deep neural network (DNN) models with different architectures.
  arXiv  Detail & Related papers  (2020-05-13T20:29:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.