search

rampasek / GraphGPS

Recipe for a General, Powerful, Scalable Graph Transformer
MIT License
643 stars 114 forks source link

Results on PATTERN #8

Closed MatthewCYM closed 1 year ago

MatthewCYM commented 2 years ago

Hi,

Thank you for your impressive work. I try to reproduce the results of SAN and GatedGCN on PATTERN using GraphGPS framework. The results are all around 89.9 test accuracy, which are significantly higher than the results reported in the paper (~85.6 test accuracy).

I understand that you report the results from benchmarking gnn. May I ask if you have encountered same issue during the experiments?

The config file I use is in config.zip

Thank you!

Yiming

rampasek commented 1 year ago

Hi @MatthewCYM,

Thank you for bringing this up and sorry for the delay. I found that there was a mistake in GraphGPS evaluation, I used plain accuracy as the evaluation metric, and not the weighted accuracy. I have now fixed the code and redone the GPS experiments, please see #12 .

Best, Ladislav