GraphSage doesn't learn. about gnn-comparison HOT 12 CLOSED

The outputs of the forward for GraphSAGE are all equal for the same iteration, which I think makes sense since the features are all 1.

from gnn-comparison.

Also outputs after first layer(x, edge_index) are all equal for the same training iterations.

from gnn-comparison.

Same thing occurs for IMDB-MULTI, the accuracies don't go higher than 30%

from gnn-comparison.

Hi, I'm investigating. It's possible it has to do with the newer version of PyG compared to 2020. Have you tried other social/chemical datasets rather than IMDB?

from gnn-comparison.

It is working on my laptop. IMDB-BINARY learns when considering the degree.

Here are the steps to reproduce

• source install.sh

Could you please double check that you are executing the commands correctly?

• python PrepareDatasets.py DATA/SOCIAL_DEGREE --dataset-name IMDB-BINARY --use-degree --outer-k 10
• cp -r DATA/SOCIAL_DEGREE/IMDB-BINARY/ DATA
• python Launch_Experiments.py --config-file config_GraphSAGE.yml --dataset-name IMDB-BINARY --result-folder RESULTS --debug

Thanks,
Federico

from gnn-comparison.

I ran the same exact commands and the error persists :(

from gnn-comparison.

Deleted the folder Data and ran the commands you mention and now it seems to work. I don't know what was blocking it from learning but anyways thank you.

from gnn-comparison.

I''m baffled as well.. happy to help! :)

from gnn-comparison.

python PrepareDatasets.py DATA/SOCIAL_1 --dataset-name IMDB-BINARY --use-one --outer-k 10
cp -r DATA/SOCIAL_1/IMDB-BINARY/ DATA
python Launch_Experiments.py --config-file config_GraphSAGE.yml --dataset-name IMDB-BINARY --result-folder RESULTS --debug

For SOCIAL_1 keeps not working :(

from gnn-comparison.

And this happens for all social datasets with use_one

from gnn-comparison.

Thanks for raising the problem. Apparently setting conv.aggr after initialization does not work anymore, so I updated the code and now GraphSAGE learns with "add" aggregation on SOCIAL_1 IMDB-BINARY.

Please pull and retry!

from gnn-comparison.

Working now. Thank you.

from gnn-comparison.