search

RUCAIBox / NCL

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

请问一下两个对比学习中的负样本是怎么选取的？ #55

Closed ning1445 closed 10 months ago

hyp1231 commented 11 months ago

如 https://github.com/RUCAIBox/NCL/blob/0aaf7c8d5a1036d9493c47b5cb6888ca20c814a9/ncl.py#L148-L206 所示，我们使用全部的用户/商品作为对比学习损失的负样本。