powerful-gnns icon indicating copy to clipboard operation
powerful-gnns copied to clipboard

Published 20 hours ago • verified publisher icon weihua916

COLLAB

Open deepdata-foundation opened this issue 5 years ago • 4 comments

Dear Author,

I could reproduce task including MYTAG,PTC,NCl1,PROTEINS,IMDB-B,IMDB-M,RDT-M5K using the parameters of your paper, however, I could not reproduce the results for RDT-B and COLLAB using the parameters.

Might I get your advice or suggestion about reproducing the results of COLLAB and RDT-B.

Regards

deepdata-foundation avatar May 09 '19 00:05 deepdata-foundation

hello, the code does not have a validation set, how to get the test set result.

LYF14020510036 avatar May 10 '19 12:05 LYF14020510036

I reviewer the closed topic and try the --degree_as_tag

deepdata-foundation avatar May 14 '19 10:05 deepdata-foundation

Dear Author,

I could reproduce task including MYTAG,PTC,NCl1,PROTEINS,IMDB-B,IMDB-M,RDT-M5K using the parameters of your paper, however, I could not reproduce the results for RDT-B and COLLAB using the parameters.

Might I get your advice or suggestion about reproducing the results of COLLAB and RDT-B.

Regards

Hi, I want to ask how do you reproduce the results? Like the MYTAG, I tried all the combinations of the paper's mentioned hyper-parameters......

Thx!!!!!!!!!!!!!

mulinmeng avatar Aug 04 '19 06:08 mulinmeng

Two quick points you can confirm are:

  • Have you correctly specified --graph_pooling_type? We used the sum graph pooling for bio/chemistry datasets and the mean graph pooling for social network datasets.
  • Have you added --deg_as_tag (use the node degree as the input node feature) for IMDB and COLLAB?

weihua916 avatar Apr 22 '21 02:04 weihua916