Controlling Popularity Bias in Learning-to-Rank Recommendation

被引:218
作者
Abdollahpouri, Himan [1 ]
Burke, Robin [1 ]
Mobasher, Bamshad [1 ]
机构
[1] Depaul Univ, Chicago, IL 60604 USA
来源
PROCEEDINGS OF THE ELEVENTH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'17) | 2017年
基金
美国国家科学基金会;
关键词
Recommender systems; long-tail; Recommendation evaluation; Coverage; Learning to rank;
D O I
10.1145/3109859.3109912
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many recommendation algorithms suffer from popularity bias in their output: popular items are recommended frequently and less popular ones rarely, if at all. However, less popular, long-tail items are precisely those that are often desirable recommendations. In this paper, we introduce a flexible regularization-based framework to enhance the long-tail coverage of recommendation lists in a learning-to-rank algorithm. We show that regularization provides a tunable mechanism for controlling the trade-off between accuracy and coverage. Moreover, the experimental results using two data sets show that it is possible to improve coverage of long tail items without substantial loss of ranking performance.
引用
收藏
页码:42 / 46
页数:5
相关论文
共 50 条
[21]   Learning to lurker rank: an evaluation of learning-to-rank methods for lurking behavior analysis [J].
Perna, Diego ;
Interdonato, Roberto ;
Tagarelli, Andrea .
SOCIAL NETWORK ANALYSIS AND MINING, 2018, 8 (01)
[22]   On the Suitability of Diversity Metrics for Learning-to-Rank for Diversity [J].
Santos, Rodrygo L. T. ;
Macdonald, Craig ;
Ounis, Iadh .
PROCEEDINGS OF THE 34TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR'11), 2011, :1185-1186
[23]   A learning-to-rank method for information updating task [J].
Minh Quang Nhat Pham ;
Minh Le Nguyen ;
Bach Xuan Ngo ;
Akira Shimazu .
Applied Intelligence, 2012, 37 :499-510
[24]   A learning-to-rank method for information updating task [J].
Minh Quang Nhat Pham ;
Minh Le Nguyen ;
Bach Xuan Ngo ;
Shimazu, Akira .
APPLIED INTELLIGENCE, 2012, 37 (04) :499-510
[25]   Rax: Composable Learning-to-Rank using JAX [J].
Jagerman, Rolf ;
Wang, Xuanhui ;
Zhuang, Honglei ;
Qin, Zhen ;
Bendersky, Michael ;
Najork, Marc .
PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, :3051-3060
[26]   Cross-Silo Federated Learning-to-Rank [J].
Shi D.-Y. ;
Wang Y.-S. ;
Zheng P.-F. ;
Tong Y.-X. .
Ruan Jian Xue Bao/Journal of Software, 2021, 32 (03) :669-688
[27]   The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation [J].
Abdollahpouri, Himan ;
Mansoury, Masoud ;
Burke, Robin ;
Mobasher, Bamshad .
RECSYS 2020: 14TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, 2020, :726-731
[28]   Counteracting Popularity Bias in Multimedia Web API Recommendation [J].
Zhai, Dengshuai ;
Yan, Chao ;
Zhong, Weiyi ;
Ding, Shaoqi ;
Qi, Lianyong ;
Zhou, Xiaokang .
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2025,
[29]   The Impact of Differential Privacy on Recommendation Accuracy and Popularity Bias [J].
Muellner, Peter ;
Lex, Elisabeth ;
Schedl, Markus ;
Kowald, Dominik .
ADVANCES IN INFORMATION RETRIEVAL, ECIR 2024, PT IV, 2024, 14611 :466-482
[30]   Feature Selection for Learning-to-Rank using Simulated Annealing [J].
Allvi, Mustafa Wasif ;
Hasan, Mahamudul ;
Rayon, Lazim ;
Shahabuddin, Mohammad ;
Khan, Md Mosaddek ;
Ibrahim, Muhammad .
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2020, 11 (03) :699-705