A crystal fractional graph neural network fuses local graph attention on 16-atom environments with global composition fractions to predict high-entropy alloy energies at RMSE levels comparable to first-principles calculations on quaternary test structures.
5, FractionFNN is a fully connected neural network consisting of several layers, each fol- lowed by a ReLU activation function
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
physics.comp-ph 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Crystal Fractional Graph Neural Network for Energy Prediction of High-Entropy Alloys
A crystal fractional graph neural network fuses local graph attention on 16-atom environments with global composition fractions to predict high-entropy alloy energies at RMSE levels comparable to first-principles calculations on quaternary test structures.