Formula graph self-attention network for representation-domain independent materials discovery

1 code implementation • 14 Jan 2022 • Achintha Ihalage, Yang Hao

The success of machine learning (ML) in materials property prediction depends heavily on how the materials are represented for learning.

Property Prediction

Analogical discovery of disordered perovskite oxides by crystal structure information hidden in unsupervised material fingerprints

1 code implementation • 25 May 2021 • Achintha Ihalage, Yang Hao

Compositional disorder induces myriad captivating phenomena in perovskites.