Fig. 3: The impact of the GNN module in both ICs computation and formation energy prediction. | npj Computational Materials

Fig. 3: The impact of the GNN module in both ICs computation and formation energy prediction.

From: SA-GAT-SR: self-adaptable graph attention networks with symbolic regression for high-fidelity material property prediction

Fig. 3: The impact of the GNN module in both ICs computation and formation energy prediction.

a–c The ICs derived by the SAE algorithm within the GNN module, where (a–c) correspond to the ICs results for ABO3, ABX3, and AB(O∣X)3, respectively. For each property prediction task, the IC reflects the significance of a specific feature within its feature set. In the figures, EF, Egap, and ET denote formation energy, bandgap, and total energy, respectively, for convenience. d–f Comparison of the GNN model with different three feature embedding algorithms in formation energy prediction on the AB(O∣X)3 dataset. The blue diamonds and red dots represent the results on the training set and testing set, respectively. The GNN model with the fully connected network (FCN) embedding algorithm serves as a baseline, reflecting standard performance. The model with the CGCNN embedding algorithm utilizes one-hot encoding followed by the FCN to generate feature vectors.

Back to article page