Pith. sign in

Machine learning in materials genome initiative: A review

Yingli Liu et al · 2020 · DOI 10.1016/j.jmst.2020.01.067.url:

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
open at publisher browse 1 citing papers

fields

cond-mat.dis-nn 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Point Group Equivariant Graph Neural Networks for Materials

cond-mat.dis-nn · 2026-07-18 · conditional · novelty 6.0

Partitioning equivariant GNN weights by crystal point-group irreps shows that trivial (A1) blocks carry most predictive signal, letting a lean A1-only model match or beat SO(3)-equivariant baselines on elastic and dielectric tensors.

citing papers explorer

Showing 1 of 1 citing paper.

  • Point Group Equivariant Graph Neural Networks for Materials cond-mat.dis-nn · 2026-07-18 · conditional · none · ref 2

    Partitioning equivariant GNN weights by crystal point-group irreps shows that trivial (A1) blocks carry most predictive signal, letting a lean A1-only model match or beat SO(3)-equivariant baselines on elastic and dielectric tensors.