Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEntropy-based Active Learning of Graph Neural Network Surrogate Models for Materials Properties
92
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Graph neural networks, trained on experimental or calculated data are becoming an increasingly important tool in computational materials science. Networks, once trained, are able to make highly accurate predictions at a fraction of the cost of experiments or first-principles calculations of comparable accuracy. However these networks typically rely on large databases of labelled experiments to train the model. In scenarios where data is scarce or expensive to obtain this can be prohibitive. By building a neural network that provides a confidence on the predicted properties, we are able to develop an active learning scheme that can reduce the amount of labelled data required, by identifying the areas of chemical space where the model is most uncertain. We present a scheme for coupling a graph neural network with a Gaussian process to featurise solid-state materials and predict properties textit{including} a measure of confidence in the prediction. We then demonstrate that this scheme can be used in an active learning context to speed up the training of the model, by selecting the optimal next experiment for obtaining a data label. Our active learning scheme can double the rate at which the performance of the model on a test data set improves with additional data compared to choosing the next sample at random. This type of uncertainty quantification and active learning has the potential to open up new areas of materials science, where data are scarce and expensive to obtain, to the transformative power of graph neural networks.
rate research
Read More
Recent application of neural networks (NNs) to modeling interatomic interactions has shown the learning machines encouragingly accurate performance for select elemental and multicomponent systems. In this study, we explore the possibility of building a library of NN-based models by introducing a hierarchical NN training. In such a stratified procedure NNs for multicomponent systems are obtained by sequential training from the bottom up: first unaries, then binaries, and so on. Advantages of constructing NN sets with shared parameters include acceleration of the training process and intact description of the constituent systems. We use an automated generation of diverse structure sets for NN training on density functional theory-level reference energies. In the test case of Cu, Pd, Ag, Cu-Pd, Cu-Ag, Pd-Ag, and Cu-Pd-Ag systems, NNs trained in the traditional and stratified fashions are found to have essentially identical accuracy for defect energies, phonon dispersions, formation energies, etc. The models robustness is further illustrated via unconstrained evolutionary structure searches in which the NN is used for the local optimization of crystal unit cells.
Graph neural networks (GNN) have been shown to provide substantial performance improvements for representing and modeling atomistic materials compared with descriptor-based machine-learning models. While most existing GNN models for atomistic predictions are based on atomic distance information, they do not explicitly incorporate bond angles, which are critical for distinguishing many atomic structures. Furthermore, many material properties are known to be sensitive to slight changes in bond angles. We present an Atomistic Line Graph Neural Network (ALIGNN), a GNN architecture that performs message passing on both the interatomic bond graph and its line graph corresponding to bond angles. We demonstrate that angle information can be explicitly and efficiently included, leading to improved performance on multiple atomistic prediction tasks. We use ALIGNN models for predicting 52 solid-state and molecular properties available in the JARVIS-DFT, Materials project, and QM9 databases. ALIGNN can outperform some previously reported GNN models on atomistic prediction tasks by up to 85 % in accuracy with better or comparable model training speed.
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.
Reinforcement learning is a promising paradigm for solving sequential decision-making problems, but low data efficiency and weak generalization across tasks are bottlenecks in real-world applications. Model-based meta reinforcement learning addresses these issues by learning dynamics and leveraging knowledge from prior experience. In this paper, we take a closer look at this framework, and propose a new Thompson-sampling based approach that consists of a new model to identify task dynamics together with an amortized policy optimization step. We show that our model, called a graph structured surrogate model (GSSM), outperforms state-of-the-art methods in predicting environment dynamics. Additionally, our approach is able to obtain high returns, while allowing fast execution during deployment by avoiding test time policy gradient optimization.
In materials science and engineering, one is typically searching for materials that exhibit exceptional performance for a certain function, and the number of these materials is extremely small. Thus, statistically speaking, we are interested in the identification of *rare phenomena*, and the scientific discovery typically resembles the proverbial hunt for the needle in a haystack.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
