uCTRL: Unbiased Contrastive Representation Learning via Alignment and Uniformity for Collaborative Filtering

Lee, Jae-woong; Park, S; Yoon, Moon‐Young; Lee, Jongwuk

doi:10.1145/3539618.3592076

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in [38], the authors proved that optimizing for contrastive loss amplifies AU's efficacy, which will bring positive effects to downstream tasks. Furthermore, uCTRL [25] acknowledges the influence of DirectAU and its use of contrastive representation learning. Therefore, in light of these considerations and the evolving understanding of CL, particularly in the context of recommendation systems, we have included DirectAU and similar methodologies in the category of contrastive learning-based methods in our research.…”

Section: More Detailed Discussionmentioning

confidence: 99%

RecDCL: Dual Contrastive Learning for Recommendation

Zhang,

Geng,

Gong

et al. 2024

Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by contrasting the embeddings between raw and augmented data. However, existing CL-based methods mostly focus on contrasting in a batch-wise way, failing to exploit potential regularity in the feature dimension. This leads to redundant solutions during the representation learning of users and items. In this work, we investigate how to employ both batch-wise CL (BCL) and feature-wise CL (FCL) for recommendation. We theoretically analyze the relation between BCL and FCL, and find that combining BCL and FCL helps eliminate redundant solutions but never misses an optimal solution. We propose a dual contrastive learning recommendation framework-RecDCL. In RecDCL, the FCL objective is designed to eliminate redundant solutions on user-item positive pairs and to optimize the uniform distributions within users and items using a polynomial kernel for driving the representations to be orthogonal; The BCL objective is utilized to generate contrastive embeddings on output vectors for enhancing the robustness of the representations. Extensive experiments on four widely-used benchmarks and one industry dataset demonstrate that RecDCL can consistently outperform the state-ofthe-art GNNs-based and SSL-based models (with an improvement of up to 5.65% in terms of Recall@20). The source code is publicly available 1 . CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Section: More Detailed Discussionmentioning

confidence: 99%