Prototypical Contrastive Learning through Alignment and Uniformity for Recommendation

TL;DR

This paper introduces ProtoAU, a prototype-based contrastive learning method for recommendation systems that avoids sampling bias and collapse issues by aligning and maintaining uniformity of prototypes, leading to improved link prediction performance.

Contribution

ProtoAU leverages prototypes as latent space anchors to eliminate random sampling in contrastive learning, and employs alignment and uniformity objectives to prevent collapse, advancing graph-based recommendation methods.

Findings

ProtoAU outperforms existing methods on four datasets.

Prototypes ensure consistency across augmentations.

Alignment and uniformity prevent trivial solutions.

Abstract

Graph Collaborative Filtering (GCF), one of the most widely adopted recommendation system methods, effectively captures intricate relationships between user and item interactions. Graph Contrastive Learning (GCL) based GCF has gained significant attention as it leverages self-supervised techniques to extract valuable signals from real-world scenarios. However, many methods usually learn the instances of discrimination tasks that involve the construction of contrastive pairs through random sampling. GCL approaches suffer from sampling bias issues, where the negatives might have a semantic structure similar to that of the positives, thus leading to a loss of effective feature representation. To address these problems, we present the \underline{Proto}typical contrastive learning through \underline{A}lignment and \underline{U}niformity for recommendation, which is called \textbf{ProtoAU}. 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. Furthermore, the absence of explicit negatives means that directly optimizing the consistency loss between instance and prototype could easily result in dimensional collapse issues. Therefore, we propose aligning and maintaining uniformity in the prototypes of users and items as optimization objectives to prevent falling into trivial solutions. Finally, we conduct extensive experiments on four datasets and evaluate their performance on the task of link prediction. Experimental results demonstrate that the proposed ProtoAU outperforms other representative methods. The source codes of our proposed ProtoAU are available at \url{https://github.com/oceanlvr/ProtoAU}.