Polymer Property Prediction via Fusion of Language Models and Probabilistic Edge Graph Neural Networks

Araki Wakiuchi, Arifin, Ryo Yoshida

Keywords: machine learning, polymer science

TL;DR: Cross-attentive fusion of MatSciBERT and a probabilistic-edge GNN yields R² > 0.96 in polymer-property prediction.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 293