search

RUCAIBox / NCL

[WWW'22] Official PyTorch implementation for "Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning".
117 stars 20 forks source link

About alibaba dataset #38

Closed downeykking closed 1 year ago

downeykking commented 1 year ago

hello, i wonder to ask in alibaba dataset, there has 300000 users, and in the original dataset, alibaba-ifasion has 3569112 users. How do you get the 300000 users because neither the interaction filter nor value field filted has been done from alibaba.yaml. Do you just follow the paper SGL, Alibaba-iFashion is more sparse, where we randomly sample 300k users and use all their interactions over the fashion outfits. ? Thanks in advance!

linzihan-backforward commented 1 year ago

Yes, we just follow the paper SGL and use the dataset that they provide to make fair comparison.

downeykking commented 1 year ago

Yes, we just follow the paper SGL and use the dataset that they provide to make fair comparison.

Got it, thanks!