Fig. 10: The performance comparison of DenseGNN and coGN on perovskites dataset. | npj Computational Materials

Fig. 10: The performance comparison of DenseGNN and coGN on perovskites dataset.

From: DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules

Fig. 10

This figure compares coGN, DenseGNN, and DenseGNN-Lite on the perovskites dataset from Matbench. It displays crystal graph parameters (total edges, average edges per graph, total nodes, average nodes per graph) for each model using their optimal edge selection methods. Additionally, it presents the total model parameters, trainable parameters, MAE results on the test set, and the training and inference time per epoch. The average time per epoch for training and inference was calculated using the mean from 20 epochs.

Back to article page