Poster
in
Workshop: AI for Science: Progress and Promises
Xtal2DoS: Attention-based Crystal to Sequence Learning for Density of States Prediction
Junwen Bai · Yuanqi Du · Yingheng Wang · Shufeng Kong · John Gregoire · Carla Gomes
Keywords: [ Attention ] [ Scientific Discovery ] [ sequence learning ] [ machine learning ] [ transformer ] [ GNN ]
Modern machine learning techniques have been extensively applied to the materials science, especially for property prediction tasks. A majority of these methods address the scalar property predictions, while more challenging spectral properties remain less emphasized. We formulate a crystal-to-sequence learning task and propose a novel attention-based learning method, Xtal2DoS, which decodes the sequential representation of material density of states (DoS) properties by incorporating the learned atomic embeddings through attention networks. Experiments show Xtal2DoS is faster than the existing models, and consistently outperforms other state-of-the-art methods on four metrics for two fundamental spectral properties, phonon and electronic DoS.