Controlling Popularity Bias in Learning-to-Rank Recommendation

被引：237

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

页码：42 / 46

页数：5

共 50 条

[41] Alleviating the recommendation bias via rank aggregation [J].

Dong, Qiang ;

Yuan, Quan ;

Shi, Yang-Bo .

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2019, 534

[42] Mitigating Popularity Bias in Recommendation: Potential and Limits of Calibration Approaches [J].

Klimashevskaia, Anastasiia ;

Elahi, Mehdi ;

Jannach, Dietmar ;

Trattner, Christoph ;

Skjaerven, Lars .

ADVANCES IN BIAS AND FAIRNESS IN INFORMATION RETRIEVAL, BIAS 2022, 2022, 1610 :82-90

[43] Enhancing Recommendation Quality of the SASRec Model by Mitigating Popularity Bias [J].

Koneru, Venkata Harshit ;

Neufeld, Xenija ;

Loth, Sebastian ;

Gruen, Andreas .

PROCEEDINGS OF THE EIGHTEENTH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2024, 2024, :781-783

[44] Incorporating Query-Specific Feedback into Learning-to-Rank Models [J].

Can, Ethem F. ;

Croft, W. Bruce ;

Manmatha, R. .

SIGIR'14: PROCEEDINGS OF THE 37TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2014, :1035-1038

[45] Learning-to-Rank and Relevance Feedback for Literature Appraisal in Empirical Medicine [J].

Lagopoulos, Athanasios ;

Anagnostou, Antonios ;

Minas, Adamantios ;

Tsoumakas, Grigorios .

EXPERIMENTAL IR MEETS MULTILINGUALITY, MULTIMODALITY, AND INTERACTION (CLEF 2018), 2018, 11018 :52-63

[46] A Bayesian Approach to Sparse Learning-to-Rank for Search Engine Optimization [J].

Krasotkina, Olga ;

Mottl, Vadim .

MACHINE LEARNING AND DATA MINING IN PATTERN RECOGNITION, MLDM 2015, 2015, 9166 :382-394

[47] Deep Neural Network Regularization for Feature Selection in Learning-to-Rank [J].

Rahangdale, Ashwini ;

Raut, Shital .

IEEE ACCESS, 2019, 7 :53988-54006

[48] Quality versus efficiency in document scoring with learning-to-rank models [J].

Capannini, Gabriele ;

Lucchese, Claudio ;

Nardini, Franco Maria ;

Orlando, Salvatore ;

Perego, Raffaele ;

Tonellotto, Nicola .

INFORMATION PROCESSING & MANAGEMENT, 2016, 52 (06) :1161-1177

[49] PlayerRank: Leveraging Learning-to-Rank AI for Player Positioning in Cricket [J].

Hassan, Bilal ;

Clough, Clare ;

Siddiqi, Yusra ;

Faizan Ali, Rao ;

Arshed, Muhammad Asad .

IEEE ACCESS, 2024, 12 :177504-177519

[50] An Empirical Study of the Impact of Field Features in Learning-to-rank Method [J].

Yang, Hua ;

Goncalves, Teresa .

INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2021, 2021, 13113 :176-187

← 1 2 3 4 5 →