Skip to main content
. 2022 Jan 21;7(4):3713–3721. doi: 10.1021/acsomega.1c06389

Figure 2.

Figure 2

Contribution evaluation of the node heterogeneity. The performance comparison between the MolHGT models with (MolHGT) and without (MolHGT-HNode) the settings of heterogeneous nodes for the (a) regression data sets and (b) classification data sets. The regression models were evaluated for the metric RMSE (the smaller, the better). Also, the classification models were evaluated for the metric AUC (the larger, the better).