Loading [MathJax]/extensions/MathZoom.js
GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation | IEEE Journals & Magazine | IEEE Xplore

GDSRec: Graph-Based Decentralized Collaborative Filtering for Social Recommendation


Abstract:

Generating recommendations based on user-item interactions and user-user social relations is a common use case in web-based systems. These connections can be naturally re...Show More

Abstract:

Generating recommendations based on user-item interactions and user-user social relations is a common use case in web-based systems. These connections can be naturally represented as graph-structured data and thus utilizing graph neural networks (GNNs) for social recommendation has become a promising research direction. However, existing graph-based methods fails to consider the bias offsets of users (items). For example, a low rating from a fastidious user may not imply a negative attitude toward this item because the user tends to assign low ratings in common cases. Such statistics should be considered into the graph modeling procedure. While some past work considers the biases, we argue that these proposed methods only treat them as scalars and can not capture the complete bias information hidden in data. Besides, social connections between users should also be differentiable so that users with similar item preference would have more influence on each other. To this end, we propose Graph-Based Decentralized Collaborative Filtering for Social Recommendation (GDSRec). GDSRec treats the biases as vectors and fuses them into the process of learning user and item representations. The statistical bias offsets are captured by decentralized neighborhood aggregation while the social connection strength is defined according to the preference similarity and then incorporated into the model design. We conduct extensive experiments on two benchmark datasets to verify the effectiveness of the proposed model. Experimental results show that the proposed GDSRec achieves superior performance compared with state-of-the-art related baselines. Our implementations are available in https://github.com/MEICRS/GDSRec.
Published in: IEEE Transactions on Knowledge and Data Engineering ( Volume: 35, Issue: 5, 01 May 2023)
Page(s): 4813 - 4824
Date of Publication: 25 February 2022

ISSN Information:

Funding Agency:


1 Introduction

In the face of a huge number of web users and information explosion, recommender systems are of vital importance which can alleviate information overload and provide users with more efficient and high-quality services. An effective recommender system can benefit both users by acquiring their preferred contents (e.g., movies, music, merchandise) from a large amount of information, and service providers by reducing promotional costs. As a result, recommender systems have attracted widespread interests in recent years. Meanwhile, exploiting social relations to improve the performance of recommendation has also become increasingly popular with the growth of social media [1], [2], [3]. In social networks, there is a flow of information among connected friends. A user’s preference is similar to or influenced by the people around him/her, which has been proved by social correlation theories [4], [5].

References

References is not available for this document.