so many bugs when gcn=False ?

Question

so many bugs when gcn=False ?

xuChenSJTU opened this issue 6 years ago · 3 comments

xuChenSJTU commented 6 years ago

It seems that the aggregator does not work and the settings here is also strange

Answer 1 · 2019-06-04T05:23:17.000Z

And these bugs only appear when in GPU training mode.

Answer 2 · 2019-11-08T10:51:55.000Z

I have encountered the same problem, how did you solve it?

Answer 3 · 2020-04-13T17:02:20.000Z

These settings work for me:

agg1 = MeanAggregator(features, cuda=False)
enc1 = Encoder(features, 1433, 128, adj_lists, agg1, gcn=False, cuda=False)
agg2 = MeanAggregator(lambda nodes : enc1(nodes).t(), cuda=False)
enc2 = Encoder(lambda nodes : enc1(nodes).t(), enc1.embed_dim, 128, adj_lists, agg2,
base_model=enc1, gcn=False, cuda=False)

My results:
Test score: 0.856551413074322
Test accuracy: 0.8379999995231628