search

qitianwu / NodeFormer

The official implementation of NeurIPS22 spotlight paper "NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification"
291 stars 28 forks source link

Deezer Europe Dataset on SGFormer/NodeFormer #19

Closed ryandeng1 closed 6 months ago

ryandeng1 commented 6 months ago

Hi,

In the SGFormer paper, that paper claims that NodeFormer achieves a 66% test accuracy on the DeezerEurope dataset, whereas on the NodeFormer paper, the paper claims that NodeFormer achieves a 71% test accuracy on the DeezerEurope dataset.

Which one is accurate, and what is the reason for the discrepancy? I ran the NodeFormer code on the DeezerEurope dataset and got around 71% test accuracy.

Thanks

qitianwu commented 6 months ago

Hi,

As explictly indicated in our papers, for NodeFormer, we use ROC-AUC as the evaluation metric on DeezerEurope, and for SGFormer, we use Accuracy.

ryandeng1 commented 6 months ago

Thank you, I missed that when reading the paper.