Questions about the new datasets

[liu-jc]

Hi authors,
I have read your paper, which is quite interesting. Thank you for your great work. But I have a question about the new datasets you use in the paper. For Cornell, Texas, and Wisconsin datasets, they are webpage networks, which are obtained from WebKB. I took a look at the original description. I don't understand how to extract the hyperlink information between different webpages. Could you please point out? Thanks!

[chennnM]

Hi Liu, we used the preprocessed data of geom directly in the experiment. Maybe you could try contacting the authors of geom for a detailed reply.

[liu-jc]

Hi Ming,

Thanks for your reply. I have already done so. An additional question about the datasets. I have noticed that you only use Chameleon dataset and don't use Squirrel dataset, which is included in Geom-GCN. I am curious about the reason. Is it about the scalability? or anything else? Would you mind sharing any insights about this? Thank you so much!