research-article

Re‐ranking with multiple objective optimization in recommender system

Authors:

Md Zakirul Alam BhuiyanAuthors Info & Claims

Transactions on Emerging Telecommunications Technologies, Volume 33, Issue 1

https://doi.org/10.1002/ett.4398

Published: 09 January 2022 Publication History

Abstract

The ranking algorithm in the recommender system aims at optimizing accuracy during training so that it pays too much attention to the relevance of the individual and ignores the mutual influence between the items in the list. In response to this problem, we propose dither, a re‐ranking model for the recommender system. We deploy the re‐ranking algorithm as an independent module after the ranking algorithm to achieve the function of decoupling from it. Our model formalizes the re‐ranking problem as a multi‐objective optimization problem. It re‐ranks the initial ranking list by balancing multiple indicators to generate an improved list and updates the list during frequent user interactions with the system. Through a case study on the MovieLens 100 K data set, the workflow, and effects of the dither model are demonstrated. In addition, the re‐ranking algorithm shows the performance advantages of our model over existing methods.

Graphical Abstract

Our model deploys the re‐ranking algorithm as an independent module after the ranking algorithm to achieve decoupling from the ranking algorithm. We formalize the re‐ranking problem as a multi‐objective optimization problem.

References

[1]

Benjula Anbu Malar M, Prabhu J. A distributed collaborative trust service recommender system for secure cloud computing. Trans Emerg Telecommun Technol. 2020;31(12):e3991.

Digital Library

[2]

Chen L, Xu Y, Xie F, Huang M, Zheng Z. Data poisoning attacks on neighborhood‐based recommender systems. Trans Emerg Telecommun Technol. 2021;32(6):e3872.

Digital Library

[3]

Li C, Feng H, de Rijke M. Cascading hybrid bandits: online learning to rank for relevance and diversity. Proceedings of the 14th ACM Conference on Recommender Systems; 2020:33‐42.

[4]

Zolaktaf Z, Babanezhad R, Pottinger R. A generic top‐n recommendation framework for trading‐off accuracy, novelty, and coverage. Proceedings of the 34th IEEE International Conference on Data Engineering; 2018:149‐160.

[5]

Chakraborty J, Verma V. Diversification in Tag Recommendation System Using Binomial Framework. New York, NY: Information and Communication Technology for Sustainable Development. Springer; 2018:423‐430.

[6]

Lu F, Tintarev N. A diversity adjusting strategy with personality for music recommendation. Proceedings of the 12th ACM Conference on Recommender Systems; 2018:7‐14.

[7]

Wang X, Qi J, Ramamohanarao K, Sun Y, Li B, Zhang R. A joint optimization approach for personalized recommendation diversification. Proceedings of the 22nd Pacific‐Asia Conference on Advances in Knowledge Discovery and Data Mining; 2018:597‐609.

[8]

Srinivasan U, Mani C. Diversity‐ensured semantic movie recommendation by applying linked open data. Int J Intell Eng Syst. 2018;11(2):275‐286.

[9]

Chen L, Zhang G, Zhou H. Fast greedy MAP inference for determinantal point process to improve recommendation diversity. Proceedings of the 32nd International Conference on Neural Information Processing Systems; 2018:5627‐5638.

[10]

Wilhelm M, Ramanathan A, Bonomo A, Jain S, Chi EH, Gillenwater J. Practical diversified recommendations on youtube with determinantal point processes. Proceedings of the 27th ACM International Conference on Information and Knowledge Management; 2018:2165‐2173.

[11]

Wang Q, Yu J, Deng W. An adjustable re‐ranking approach for improving the individual and aggregate diversities of product recommendations. Electron Commerce Res. 2019;19(1):59‐79.

Digital Library

[12]

Steck H. Calibrated recommendations. Proceedings of the 12th ACM Conference on Recommender Systems; 2018:154‐162.

[13]

Sürer Ö, Burke R, Malthouse EC. Multistakeholder recommendation with provider constraints. Proceedings of the 12th ACM Conference on Recommender Systems; 2018:54‐62.

[14]

Karako C, Manggala P. Using image fairness representations in diversity‐based re‐ranking for recommendations. Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization; 2018:23‐28.

[15]

Geyik SC, Ambler S, Kenthapadi K. Fairness‐aware ranking in search and recommendation systems with application to linkedin talent search. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2019:2221‐2231.

[16]

Abdollahpouri H. Incorporating system‐level objectives into recommender systems. Proceedings of the Web Conference; 2019:2‐6.

[17]

Liu W, Guo J, Sonboli N, Burke R, Zhang S. Personalized fairness‐aware re‐ranking for microlending. Proceedings of the 13th ACM Conference on Recommender Systems; 2019:467‐471.

[18]

Abdollahpouri H. Popularity bias in ranking and recommendation. Proceedings of the 2nd AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society; 2019:529‐530.

[19]

Miyamoto S, Zamami T, Yamana H. Improving recommendation diversity across uers by reducing frequently recommended items. Proceedings of the 6th IEEE International Conference on Big Data; 2018:5392‐5394.

[20]

Miyamoto S, Zamami T, Yamana H. Appearance frequency‐based ranking method for improving recommendation diversity. Proceedings of the 4th IEEE International Conference on Big Data Analytics; 2019:420‐425.

[21]

Afridi AH. User control and serendipitous recommendations in learning environments. Proceedings of the 9th International Conference on Ambient Systems, Networks and Technologies; 2018:214‐221.

[22]

Swezey RM, Charron B. Large‐scale recommendation for portfolio optimization. Proceedings of the 12th ACM Conference on Recommender Systems; 2018:382‐386.

[23]

Wasilewski J, Hurley N. Intent‐aware item‐based collaborative filtering for personalised diversification. Proceedings of the 26th Conference on User Modeling, Adaptation and Personalization; 2018:81‐89.

[24]

Kaya M, Bridge D. Community‐aware diversification of recommendations. Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing; 2019:1639‐1646.

[25]

Elsafty A, Riedl M, Biemann C. Document‐based recommender system for job postings using dense representations. Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies; 2018:216‐224.

[26]

Katariya S, Bose J, Reddy MV, Sharma A, Tappashetty S. A personalized health recommendation system based on smartphone calendar events. Proceedings of the 16th International Conference on Smart Homes and Health Telematics; 2018:110‐120.

[27]

Ferraro A, Jannach D, Serra X. Exploring longitudinal effects of session‐based recommendations. Proceedings of the 14th ACM Conference on Recommender Systems; 2020:474‐479.

[28]

Gong Y, Jiang Z, Feng Y, et al. EdgeRec:recommender system on edge in mobile taobao. Proceedings of the 29th ACM International Conference on Information and Knowledge Management; 2020:2477‐2484.

[29]

Hsueh YL, Huang HM. Personalized itinerary recommendation with time constraints using GPS datasets. Knowl Inf Syst. 2019;60(1):523‐544.

Digital Library

[30]

Yan Y, Liu Z, Zhao M, Guo W, Yan WP, Bao Y. A practical deep online ranking system in e‐commerce recommendation. Proceedings of the 26th European Conference on Machine Learning and Knowledge Discovery in Databases; 2018:186‐201.

[31]

Ai Q, Bi K, Guo J, Croft WB. Learning a deep listwise context model for ranking refinement. Proceedings of the 41st International ACM SIGIR Conference on Research and Development in Information Retrieval; 2018:135‐144.

[32]

Lian J, Zhang F, Xie X, Sun G. Towards better representation learning for personalized news recommendation: a multi‐Channel deep fusion approach. Proceedings of the 28th International Joint Conference on Artificial Intelligence; 2018:3805‐3811.

[33]

Pei C, Zhang Y, Zhang Y, et al. Personalized re‐ranking for recommendation. Proceedings of the 13th ACM Conference on Recommender Systems; 2019:3‐11.

[34]

Gudla SK, Bose J, Sane KR. Enhanced service recommender and ranking system using browsing patterns of users. Proceedings of the 16th IEEE Annual Consumer Communications and Networking Conference; 2019:1‐6.

[35]

Borodin A, Jain A, Lee HC, Ye Y. Max‐sum diversification, monotone submodular functions, and dynamic updates. Acm Trans Algorithms. 2017;13(3):1‐25.

Digital Library

[36]

Hassin R, Rubinstein S, Tamir A. Approximation algorithms for maximum dispersion. Operat Res Lett. 1997;21(3):133‐137.

Digital Library

[37]

Harper FM, Konstan JA. The movieLens datasets: history and context. Acm Trans Interact Intell Syst. 2015;5(4):1‐19.

Digital Library

Cited By

Xi YLiu WDai XTang RLiu QZhang WYu Y(2024)Utility-Oriented Reranking with Counterfactual ContextACM Transactions on Knowledge Discovery from Data10.1145/367100418:8(1-22)Online publication date: 4-Jun-2024
https://dl.acm.org/doi/10.1145/3671004
Gong JWan YLiu YLi XZhao YWang CLin YFang XFeng WZhang JTang J(2023)Reinforced MOOCs Concept Recommendation in Heterogeneous Information NetworksACM Transactions on the Web10.1145/358051017:3(1-27)Online publication date: 1-Mar-2023
https://dl.acm.org/doi/10.1145/3580510

Index Terms

Re‐ranking with multiple objective optimization in recommender system

Index terms have been assigned to the content through auto-classification.

Recommendations

A Scalable, Accurate Hybrid Recommender System
WKDD '10: Proceedings of the 2010 Third International Conference on Knowledge Discovery and Data Mining

Recommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given resource. There are three main types of recommender systems: collaborative filtering, content-based filtering, and ...
Collaborative Multi-objective Ranking
CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge Management

This paper proposes to jointly resolve row-wise and column-wise ranking problems when an explicit rating matrix is given. The row-wise ranking problem, also known as personalized ranking, aims to build user-specific models such that the correct order of ...
A New Approach for Recommender System
ICACS '17: Proceedings of the 1st International Conference on Algorithms, Computing and Systems

In today's e-commerce environment, Collaborative Filtering (CF) is a widely used algorithm for recommender system, which is to identify the users who have similar preferences to the target user, and to predict the preference of the target user according ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Transactions on Emerging Telecommunications Technologies

Transactions on Emerging Telecommunications Technologies Volume 33, Issue 1

January 2022

479 pages

EISSN:2161-3915

DOI:10.1002/ett.v33.1

Issue’s Table of Contents

© 2021 John Wiley & Sons, Ltd.

Publisher

John Wiley & Sons, Inc.

United States

Publication History

Published: 09 January 2022

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Xi YLiu WDai XTang RLiu QZhang WYu Y(2024)Utility-Oriented Reranking with Counterfactual ContextACM Transactions on Knowledge Discovery from Data10.1145/367100418:8(1-22)Online publication date: 4-Jun-2024
https://dl.acm.org/doi/10.1145/3671004
Gong JWan YLiu YLi XZhao YWang CLin YFang XFeng WZhang JTang J(2023)Reinforced MOOCs Concept Recommendation in Heterogeneous Information NetworksACM Transactions on the Web10.1145/358051017:3(1-27)Online publication date: 1-Mar-2023
https://dl.acm.org/doi/10.1145/3580510

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents