Enhancing Structure–Property Relationships in Porous Materials through Transfer Learning and Cross-Material Few-Shot Learning

Park, Hyunsoo; Kang, Yeonghun; Kim, Jihan

doi:10.1021/acsami.3c10323

Cited by 6 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, machine learning (ML) approaches were exploited to further accelerate MOF discovery. − Based on a training sample, a descriptor-based ML model is learned, for e.g., kernel ridge regression, random forests, or gradient boosting regression trees, ,− to predict electronic and gas adsorption properties of unseen samples. Recently, deep learning methods such as crystal graph convolutional neural networks (CGCNNs , ) and transformer-based models ,, were also investigated. Despite being powerful and well-suited for large and complex data, deep-learning methods require a substantial amount of labeled data and computational resources to train a complex model.…”

Section: Introductionmentioning

confidence: 99%

Informative Training Data for Efficient Property Prediction in Metal–Organic Frameworks by Active Learning

Jose,

Devijver,

Jakse

et al. 2024

J. Am. Chem. Soc.

View full text Add to dashboard Cite

In recent data-driven approaches to material discovery, scenarios where target quantities are expensive to compute and measure are often overlooked. In such cases, it becomes imperative to construct a training set that includes the most diverse, representative, and informative samples. Here, a novel regression tree-based active learning algorithm is employed for such a purpose. It is applied to predict the band gap and adsorption properties of metal−organic frameworks (MOFs), a novel class of materials that results from the virtually infinite combinations of their building units. Simpler and low dimensional descriptors, such as those based on stoichiometric and geometric properties, are used to compute the feature space for this model owing to their ability to better represent MOFs in the low data regime. The partitions given by a regression tree constructed on the labeled part of the data set are used to select new samples to be added to the training set, thereby limiting its size while maximizing the prediction quality. Tests on the QMOF, hMOF, and dMOF data sets reveal that our method constructs small training data sets to learn regression models that predict the target properties more efficiently than existing active learning approaches, and with lower variance. Specifically, our active learning approach is highly beneficial when labels are unevenly distributed in the descriptor space and when the label distribution is imbalanced, which is often the case for real world data. The regions defined by the tree help in revealing patterns in the data, thereby offering a unique tool to efficiently analyze complex structure−property relationships in materials and accelerate materials discovery.

show abstract