Graph Bottlenecked Social Recommendation
Yonghui Yang, Le Wu, Zihan Wang, Zhuangzhuang He, Richang Hong, Meng, Wang

TL;DR
This paper introduces GBSR, a novel framework that denoises social graphs by learning minimal yet informative social structures, improving social recommendation accuracy by filtering out noisy, redundant social relations.
Contribution
The paper proposes a model-agnostic social denoising framework using an information bottleneck approach, addressing social noise in graph-based recommendations.
Findings
GBSR outperforms existing methods in recommendation accuracy.
It effectively reduces social noise and redundant relations.
Demonstrates good generality across various backbone models.
Abstract
With the emergence of social networks, social recommendation has become an essential technique for personalized services. Recently, graph-based social recommendations have shown promising results by capturing the high-order social influence. Most empirical studies of graph-based social recommendations directly take the observed social networks into formulation, and produce user preferences based on social homogeneity. Despite the effectiveness, we argue that social networks in the real-world are inevitably noisy~(existing redundant social relations), which may obstruct precise user preference characterization. Nevertheless, identifying and removing redundant social relations is challenging due to a lack of labels. In this paper, we focus on learning the denoised social structure to facilitate recommendation tasks from an information bottleneck perspective. Specifically, we propose a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRecommender Systems and Techniques · Advanced Graph Neural Networks · Complex Network Analysis Techniques
MethodsFocus
