Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation

1 code implementation • 3 Feb 2024 • Yangxun Ou, Lei Chen, Fenglin Pan, Yupeng Wu

Specifically, we first propose prototypes (cluster centroids) as a latent space to ensure consistency across different augmentations from the origin graph, aiming to eliminate the need for random sampling of contrastive pairs.

Collaborative Filtering Contrastive Learning +1