基于自监督学习的去流行度偏差推荐方法

张帅; 高旻; 文俊浩; 熊庆宇; 唐旭

doi:10.12263/DZXB.20210443

您当前的位置：

首页 >

文章列表页 >

基于自监督学习的去流行度偏差推荐方法

学术论文 | 更新时间：2025-12-08

- 基于自监督学习的去流行度偏差推荐方法
- Self-Supervised Learning for Alleviating Popularity Bias in Recommender Systems
- 电子学报 2022年50卷第10期页码：2361-2371
- 作者机构：
  
  1.信息物理社会可信服务计算教育部重点实验室（重庆大学），重庆 400044
  2.重庆大学大数据与软件学院，重庆 400044
- 作者简介：
  
  [ "张帅男，1997年生.现为重庆大学大数据与软件学院在读硕士研究生.主要研究方向为机器学习、推荐系统等.E-mail: zhangshuai@cqu.edu.cn" ]
  [ "高旻（通讯作者）女，1980年生.工学博士.重庆大学大数据与软件学院副教授、硕士生导师.主要研究方向为推荐系统、异常检测、社会媒体挖掘." ]
  [ "文俊浩男，1969年生.工学博士.重庆大学软件学院教授.主要研究方向为计算智能与推荐系统.E-mail: jhwen@cqu.edu.cn" ]
  [ "熊庆宇男，1965年生.工学博士.重庆大学大数据与软件学院教授、博士生导师.主要研究方向为智能控制、传感器网络和信息系统．E-mail: xiong03@cqu.edu.cn" ]
  [ "唐旭男，1983年生.现为重庆大学机械学院在读博士研究生.主要研究方向为智能制造与推荐系统.E-mail: tangxu@cqu.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(72161005);重庆市自然科学基金(cstc2020jcyj-msxmX0690);重庆大学中央高校基本科研业务费项目(2020CDJ-LHZZ-039);重庆市技术创新与应用发展专项重点项目(cstc2019jscx-fxydX0012);重庆市留学人员创业创新支持计划(cx2020097)
- DOI：10.12263/DZXB.20210443
  中图分类号： TP311;
- 收稿：2021-04-07，
  
  修回：2021-09-02，
  
  纸质出版：2022-10-25
- 稿件说明：
移动端阅览
张帅,高旻,文俊浩等.基于自监督学习的去流行度偏差推荐方法[J].电子学报,2022,50(10):2361-2371.

ZHANG Shuai,GAO Min,WEN Jun-hao,et al.Self-Supervised Learning for Alleviating Popularity Bias in Recommender Systems[J].ACTA ELECTRONICA SINICA,2022,50(10):2361-2371.
张帅,高旻,文俊浩等.基于自监督学习的去流行度偏差推荐方法[J].电子学报,2022,50(10):2361-2371. DOI： 10.12263/DZXB.20210443.

ZHANG Shuai,GAO Min,WEN Jun-hao,et al.Self-Supervised Learning for Alleviating Popularity Bias in Recommender Systems[J].ACTA ELECTRONICA SINICA,2022,50(10):2361-2371. DOI： 10.12263/DZXB.20210443.

摘要

近年来，随着推荐系统研究的不断深入，推荐系统的公平性受到越来越多关注. 流行度偏差也即流行的物品比非流行的物品更容易被推荐，是影响其公平性的重要因素之一. 流行度偏差对推荐系统的各利益相关者都有严重的影响，引起研究者的广泛关注. 相关研究主要通过推荐结果重排或学习过程中融合正则化项提升非流行物品的曝光率，而非流行物品的交互数据极度稀疏成为研究的瓶颈. 针对此问题，本文提出基于自监督学习的去流行度偏差推荐方法，解决两个难点：（1）准确学习交互数据极度稀疏的非流行物品的表征；（2）提升非流行物品曝光率的同时，兼顾不同用户对流行和非流行物品的偏好. 具体地，从用户的角度，提出流行物品和非流行物品双视图的用户偏好学习方法，准确学习用户对流行和非流行物品的真实偏好；从物品的角度，采用自监督学习，利用互信息最大化捕获非流行物品与流行物品间的潜在关系，辅助提升非流行物品嵌入学习的准确性. 最后，设计用户流行度偏好一致性、资格公平性等指标，并通过三个公开数据集的大量实验说明了本文方法在提升推荐性能的同时，能有效缓解流行度偏差问题并具有较强的通用性.

Abstract

In recent years

with the development of recommender system

more and more attention has been paid to the fairness of recommender system. Popularity bias mens that popular items are more likely to be recommended than unpopular items

which is one of the important factors affecting its fairness. Popularity bias has a serious impact on all stakeholders in the recommendation system

which has aroused widespread concern of researchers. Related research mainly improves the exposure rate of unpopular items by the rearrangement of recommended results or the integration of regularization items in the learning process

but the extremely sparse interaction data of unpopular items becomes the bottleneck of research. To solve this problem

this paper proposes self-supervised learning for alleviating popularity bias (SSLAB) to deal with two difficulties: (1) accurately learning the representation of unpopular items with extremely sparse interactive data; (2) improving the exposure rate of unpopular items while taking into account the preferences of different users for popular and unpopular items. Specifically

from the perspective of users

this paper proposes a dual view user preference learning method for popular and unpopular items to accurately learn users’ real preferences for popular and unpopular items; from the perspective of items

self-supervised learning is used to capture the potential relationship between unpopular items and popular items by maximizing mutual information to help improve the accuracy of unpopular items embedded learning. Finally

metrics such as user popularity preference consistency and qualification fairness are designed

and a large number of experiments on three open data sets show that the proposed method can effectively alleviate the popularity bias and has a strong scalability while improving the recommendation performance.

关键词

Keywords

references

ABDOLLAHPOURI H . Popularity bias in ranking and recommendation [C]// Proceedings of the 2019 AAAI/ACM Conference on AI , Ethics, and Society . Honolulu : ACM , 2019 : 529 - 530 .

VARGAS S , CASTELLS P . Improving sales diversity by recommending users to items [C]// Eighth ACM Conference on Recommender Systems . Foster City : ACM , 2014 : 145 - 152 .

MANSOURY M , ABDOLLAHPOURI H , PECHENIZKIY M , et al . Fair match: A graph-based approach for improving aggregate diversity in recommender systems [C]// Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization . Genoa : ACM , 2020 : 154 - 162 .

ABDOLLAHPOURI H , BURKE R , MOBASHER B . Managing popularity bias in recommender systems with personalized re-ranking [C]// Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference . Sarasota : AAAI Press , 2019 : 413 - 418 .

ABDOLLAHPOURI H , BURKE R , MOBASHER B . Controlling popularity bias in learning-to-rank recommendation [C]// Proceedings of the Eleventh ACM Conference on Recommender Systems . Como : ACM , 2017 : 42 - 46 .

WANG X , HE X , WANG M , et al . Neural graph collaborative filtering [C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval . Paris : ACM , 2019 : 165 - 174 .

HE X , DENG K , WANG X , et al . LightGCN: Simplifying and powering graph convolution network for recommendation [C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2020 : 639 - 648 .

陈聪 , 俞东进 , 吴建华 , 等 . 基于隐式反馈数据的个性化游戏推荐 [J]. 电子学报 , 2018 , 46 ( 11 ): 2626 - 2632 .

CHEN C , YU D J , WU J H , et al . Personalized game recommendation based on implicit feedback [J]. Acta Electronica Sinica , 2018 , 46 ( 11 ): 2626 - 2632 . (in Chinese)

郭景峰 , 朱晓松 , 李爽 . 直播电视推荐系统的评分预测算法研究 [J]. 电子学报 , 2020 , 48 ( 9 ): 1735 - 1740 .

GUO J F , ZHU X S , LI S . Research on rating algorithm of live TV recommender systems [J]. Acta Electronica Sinica , 2020 , 48 ( 9 ): 1735 - 1740 . (in Chinese)

RENDLE S , FREUDENTHALER C , GANTNER Z , et al . BPR: Bayesian personalized ranking from implicit feedback [C]// Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence . Montreal : AUAI Press , 2009 : 452 - 461 .

HJELM R , FEDOROV A , LAVOIE-MARCHILDON S , et al . Learning deep representations by mutual information estimation and maximization [C]// 7th International Conference on Learning Representations . New Orleans : OpenReview , 2019 : 233 - 256 .

KONG L , D'AUTUME C , YU L , et al . A mutual information maximization perspective of language representation learning [C]// 8th International Conference on Learning Representations . Addis Ababa : OpenReview , 2020 : 1167 - 1178 .

LINSKER R . Self-organization in a perceptual network [J]. IEEE Computer , 1988 , 21 ( 3 ): 105 - 117 .

CARSE J , CAREY F , MCKENNA S . Unsupervised representation learning from pathology images with multi-directional contrastive predictive coding [C]// 18th IEEE International Symposium on Biomedical Imaging . Nice : IEEE , 2021 : 1254 - 1258 .

ZHOU K , WANG H , ZHAO W , et al . S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization [C]// The 29th ACM International Conference on Information and Knowledge Management . Ireland : ACM , 2020 : 1893 - 1902 .

MA J , ZHOU C , YANG H , et al . Disentangled self-supervision in sequential recommenders [C]// The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining . CA : ACM , 2020 : 483 - 491 .

PARK Y J , TUZHILIN A . The long tail of recommender systems and how to leverage it [C]// Proceedings of the 2008 ACM Conference on Recommender Systems . Lausanne : ACM , 2008 : 11 - 18 .

ABDOLLAHPOURI H , MANSOURY M , BURKE R , et al . The unfairness of popularity bias in recommendation [C]// Proceedings of the Workshop on Recommendation in Multi-Stakeholder Environments Co-Located with the 13th ACM Conference on Recommender Systems , Copenhagen : CEUR-WS , 2019 : 1257 - 1263 .

PATRO G , BISWAS A , GANGULY N , et al . FairRec: Two-sided fairness for personalized recommendations in two-sided platforms [C]// Proceedings of The Web Conference 2020 . Taipei : ACM , 2020 : 1194 - 1204 .

VARDASBI A , RIJKE M , MARKOV I . Cascade model-based propensity estimation for counterfactual learning to rank [C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2020 : 2089 - 2092 .

SAITO Y , YAGINUMA S , NISHINO Y , et al . Unbiased recommender learning from missing-not-at-random implicit feedback [C]// The Thirteenth ACM International Conference on Web Search and Data Mining . Houston : ACM , 2020 : 501 - 509 .

SINHA A , GLEICH D , RAMANI K . Deconvolving feedback loops in recommender systems [C]// Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems . Barcelona : ACM , 2017 : 3243 - 3251 .

ZHENG Y , GAO C , LI X , et al . Disentangling user interest and conformity for recommendation with causal conference embedding [C]// Proceedings of The Web 2021 . Ljubljana : ACM , 2021 : 2980 - 2991 .

DEVLINJ , CHANGM , LEEK , etal . BERT: Pre-training of deepbi directional transformers for language [C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language . Minneapolis : ACL , 2019 : 4171 - 4186 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems . Long Beach : ACM , 2017 : 5998 - 6008 .

CHEN Z , XIAO R , LI C , et al . ESAM: Discriminative domain adaptation with non-displayed items to improve long-tail performance [C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development In Information Retrieval . New York : ACM , 2020 : 579 - 588 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

两方参与的隐私保护协同过滤推荐研究

直播电视推荐系统的评分预测算法研究

基于自监督图卷积和注意力机制实现隐式反馈降噪的社交推荐

融合自注意力机制的多行为图对比学习推荐方法