Loading [MathJax]/extensions/MathMenu.js
Joint Multi-Grained Popularity-Aware Graph Convolution Collaborative Filtering for Recommendation | IEEE Journals & Magazine | IEEE Xplore

Joint Multi-Grained Popularity-Aware Graph Convolution Collaborative Filtering for Recommendation


Abstract:

Graph convolution networks (GCNs), with their efficient ability to capture high-order connectivity in graphs, have been widely applied in recommender systems. Stacking mu...Show More

Abstract:

Graph convolution networks (GCNs), with their efficient ability to capture high-order connectivity in graphs, have been widely applied in recommender systems. Stacking multiple neighbor aggregation is the major operation in GCNs. It implicitly captures popularity features because the number of neighbor nodes reflects the popularity of a node. However, existing GCN-based methods ignore a universal problem: users’ sensitivity to item popularity is differentiated, but the neighbor aggregations in GCNs actually fix this sensitivity through graph Laplacian normalization, leading to suboptimal personalization. In this work, we propose to model multigrained popularity features and jointly learn them together with high-order connectivity to match the differentiation of user preferences exhibited in popularity features. Specifically, we develop a Joint Multigrained Popularity-aware Graph Convolution Collaborative Filtering model, short for JMP-GCF, which uses a popularity-aware embedding generation to construct multigrained popularity features and uses the idea of joint learning to capture the signals within and between different granularities of popularity features that are relevant for modeling user preferences. In addition, we propose a multistage stacked training strategy to speed up model convergence. We conduct extensive experiments on three public datasets to show the state-of-the-art performance of JMP-GCF. The complete codes of JMP-GCF are released at https://github.com/hfutmars/JMP-GCF.
Published in: IEEE Transactions on Computational Social Systems ( Volume: 10, Issue: 1, February 2023)
Page(s): 72 - 83
Date of Publication: 08 March 2022

ISSN Information:

Funding Agency:


I. Introduction

Personalized recommendation methods have been deployed in many applications [1], [2] to solve information overload and refine user experience in online services. Collaborative filtering (CF) [3] is the mainstream algorithm for recommender systems because of its effectiveness and low computational overload. At its core is using historical user–item interactions to incorporate collaborative signals into the embedding process.

References

References is not available for this document.