How graph convolutions amplify popularity bias for recommendation?  

作　　者：Jiajia CHEN Jiancan WU Jiawei CHEN Xin XIN Yong LI Xiangnan HE 

机构地区：[1]School of Information Science and Technology,University of Science and Technology of China,Hefei 230026,China [2]School of Computer Science and Technology,Zhejiang University,Hangzhou 310058,China [3]School of Computer Science and Technology,Shandong University,Qingdao 250100,China [4]Department of Electronic Engineering,Tsinghua University,Beijing 100084,China

出　　处：《Frontiers of Computer Science》2024年第5期121-132,共12页计算机科学前沿（英文版）

基　　金：This work was supported by the National Key R&D Program of China(2021ZD0111802);the National Natural Science Foundation of China(Grant No.19A2079);the CCCD Key Lab of Ministry of Culture and Tourism.

摘　　要：Graphconvolutional networks(GCNs)have become prevalent in recommender system(RS)due to their superiority in modeling collaborative patterns.Although improving the overall accuracy,GCNs unfortunately amplify popularity bias-tail items are less likely to be recommended.This effect prevents the GCN-based RS from making precise and fair recommendations,decreasing the effectiveness of recommender systems in the long run.In this paper,we investigate how graph convolutions amplify the popularity bias in RS.Through theoretical analyses,we identify two fundamental factors:(1)with graph convolution(i.e.,neighborhood aggregation),popular items exert larger influence than tail items on neighbor users,making the users move towards popular items in the representation space;(2)after multiple times of graph convolution,popular items would affect more high-order neighbors and become more influential.The two points make popular items get closer to almost users and thus being recommended more frequently.To rectify this,we propose to estimate the amplified effect of popular nodes on each node's representation,and intervene the effect after each graph convolution.Specifically,we adopt clustering to discover highly-influential nodes and estimate the amplification effect of each node,then remove the effect from the node embeddings at each graph convolution layer.Our method is simple and generic-it can be used in the inference stage to correct existing models rather than training a new model from scratch,and can be applied to various GCN models.We demonstrate our method on two representative GCN backbones LightGCN and UltraGCN,verifying its ability in improving the recommendations of tail items without sacrificing the performance of popular items.Codes are open-sourced^(1)).

关 键 词：RECOMMENDATION graph convolution networks popularity bias 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]