Multi-Task Learning for Material Property Prediction

Material property prediction is a critical task within material science and other related fields where the identification of advanced materials with dynamic characteristics is essential for developing innovative technologies, improving product performance, and driving scientific discoveries. The search for suitable candidate materials aimed at specific applications is traditionally conducted through time-consuming experimental methods. Conversely, computational approaches, such as density functional theory (DFT) calculations, necessitate the resolution of complex mathematical equations and significant computational resources. Machine learning (ML) models have significantly transformed this field by automating the tedious process of material searching within extensive search spaces. However, these models are unable to incorporate diverse features of varying dimensions for different materials and properties. Recently, graph convolutional neural networks (GCNNs), have been employed to analyze the complex structures of materials, thereby efficiently predicting their associated properties. In this work, we demonstrate the potential of multi-task learning (MTL) in conjunction with the GCNNs in material property prediction. Our findings suggest that the MTL framework integrated into the GCNN architecture such as Crystal Graph Convolutional Neural Network (CGCNN) and its advanced variant Orbital Graph Convolutional Neural Network (OGCNN) can enhance the generalization and efficacy of property predictions. Notably, we achieved a maximum improvement of 7.95 % in one of our setups, underscoring the potential of these models to handle multiple property predictions with considerable effectiveness.