AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction

Bin Cao, Yang Liu, Longhan Zhang, Yifan Wu, Zhixun Li, Yuyu Luo, Hong Cheng, Yang Ren, Tongyi ZHANG

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: Molecular graph pretraining · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the reciprocal-space diffraction module (ablation)PRDNet · Materials Projectband gap MAE (eV): 0.361 -> 0.151Improved
add the reciprocal-space diffraction module (ablation)PRDNet · Materials Projectformation energy MAE (eV/atom): 0.041 -> 0.028Improved
add the reciprocal-space diffraction module (ablation)PRDNet · JARVIS-DFTbulk modulus MAE (log GPa): 0.287 -> 0.064Improved
add the reciprocal-space diffraction module (ablation)PRDNet · Matbenchformation energy MAE (eV/atom): 0.042 -> 0.019Improved
use multi-head instead of single-head attention (ablation)PRDNet · Materials Projectband gap MAE (eV): 0.318 -> 0.151Improved
add residual connections (ablation)PRDNet · Materials Projectmetal/non-metal accuracy (%): 82.7 -> 93.3Improved
add edge features to attention (ablation)PRDNet · Materials Projectmetal/non-metal accuracy (%): 80.1 -> 93.3Improved
add edge features to attention (ablation)PRDNet · JARVIS-DFTband gap MAE (eV): 0.412 -> 0.140Improved
use learned pseudo-particle form factors instead of tabulated X-ray form factors (ablation)PRDNet · Materials Projectshear modulus MAE (log GPa): 0.322 -> 0.108Improved
use learned pseudo-particle form factors instead of tabulated X-ray form factors (ablation)PRDNet · Materials Projectmetal/non-metal accuracy (%): 78.9 -> 93.3Improved
attach the diffraction module to baseline CGCNNCGCNN · Materials Projectband gap MAE (eV): 0.262 -> 0.207Improved
attach the diffraction module to baseline GATGNNGATGNN · Materials Projectshear modulus MAE (log GPa): 0.111 -> 0.169Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy