Dropout inside GATConv layer

[afternone]

In the (Optional) Exercises, it is mentioned dropout inside GATConv layer, but I did not find the keywords parameter about dropout. How can I set dropout inside GATConv layer.

[CarloLucibello]

Actually, that is a missing feature. We should add the dropout option to GATConv and GATv2Conv PyG has it

[5hv5hvnk]

@CarloLucibello Can adding something like this after line 366 here can do the job?

if l.dropout > 0 && Flux.training()
        x = Flux.dropout(x, l.dropout)

[CarloLucibello]

not really, dropout is performed on the attention coefficients I think. It corresponds to masking the attention, see https://github.com/FluxML/NNlib.jl/blob/master/src/attention.jl