Skip to main content

Graph comparison

Run set 1: Grey: Old GAT Purple: GAT with the augmentation (mean pool the attentions at each layer, mean aggregate edges) - but idk why they have more parameters! Green: GraphSAGE Run et 2: composer task, as the data is better we have better comparison SAGE learns faster and have less overfitting. Conclusion: maybe GAT is not making things better.
Created on February 24|Last edited on February 24

ATEPP difficulty&composer id


Select runs that logged val_acc
to visualize data in this line chart.
Select runs that logged val_loss
to visualize data in this line chart.
Select runs that logged val_fscore
to visualize data in this line chart.
Run set
0
Run set 2
0