Skip to main content

Extensive Attention Mechanisms in Graph Neural Networks for Materials Discovery

by Guojing Cong, Talia M Ben-naim, Victor Xinhua Fung
Publication Type
Conference Paper
Book Title
2022 IEEE International Conference on Data Mining Workshops (ICDMW)
Publication Date
Page Numbers
1 to 8
Publisher Location
New Jersey, United States of America
Conference Name
IEEE International Conference on Data Mining Workshops (ICDMW)
Conference Location
Orlando, Florida, United States of America
Conference Sponsor
Conference Date

We present our research where attention mechanism is extensively applied to various aspects of graph neural net- works for predicting materials properties. As a result, surrogate models can not only replace costly simulations for materials screening but also formulate hypotheses and insights to guide further design exploration. We predict formation energy of the Materials Project and gas adsorption of crystalline adsorbents, and demonstrate the superior performance of our graph neural networks. Moreover, attention reveals important substructures that the machine learning models deem important for a material to achieve desired target properties. Our model is based solely on standard structural input files containing atomistic descriptions of the adsorbent material candidates. We construct novel methodological extensions to match the prediction accuracy of state-of-the-art models some of which were built with hundreds of features at much higher computational cost. We show that sophisticated neural networks can obviate the need for elaborate feature engineering. Our approach can be more broadly applied to optimize gas capture processes at industrial scale.