Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation
In contrast to traditional recommender systems which usually pay attention to users' general and long-term preferences, sequential recommendation (SR) can model users' dynamic intents based on their behaviour sequences and suggest the next item(s) to them. However, most of existing sequent...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/170379 |
| _version_ | 1811679705031507968 |
|---|---|
| author | Zhou, Wei Liu, Yong Li, Min Wang, Yu Shen, Zhiqi Feng, Liang Zhu, Zexuan |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Zhou, Wei Liu, Yong Li, Min Wang, Yu Shen, Zhiqi Feng, Liang Zhu, Zexuan |
| author_sort | Zhou, Wei |
| collection | NTU |
| description | In contrast to traditional recommender systems which usually pay attention to users' general and long-term preferences, sequential recommendation (SR) can model users' dynamic intents based on their behaviour sequences and suggest the next item(s) to them. However, most of existing sequential models learn the ranking score of an item only based on its relevance property, and the personalized user demands in terms of different learning objectives, such as diversity, tail novelty or recency, which have been played essential roles in multi-objective recommendation (MOR), are often neglected in SR. In this paper, we first discuss the importance of considering multiple different objectives within a learning model for recommender system. Next, to capture users' objective-level preferences by utilizing interactive information in the sequential context, we propose a novel Dynamic Multi-objective Recommendation (DMORec) framework with interactive evolution for SR. In particular, DMORec formulates a dynamic multi-objective optimization task to simultaneously optimize more than two varying objectives in an interactive recommendation process. Moreover, to resolve this optimization task in SR, we develop an evolutionary algorithm with supervised learning approach to obtain the Pareto-optimal solutions of the formulated problem. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of the proposed DMORec for dynamic multi-objective recommendation in sequential recommender systems. |
| first_indexed | 2024-10-01T03:13:24Z |
| format | Journal Article |
| id | ntu-10356/170379 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:13:24Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1703792023-09-11T02:05:59Z Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation Zhou, Wei Liu, Yong Li, Min Wang, Yu Shen, Zhiqi Feng, Liang Zhu, Zexuan School of Computer Science and Engineering Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) Engineering::Computer science and engineering Dynamic Multi-Objective Optimization Multi-Objective Recommendation In contrast to traditional recommender systems which usually pay attention to users' general and long-term preferences, sequential recommendation (SR) can model users' dynamic intents based on their behaviour sequences and suggest the next item(s) to them. However, most of existing sequential models learn the ranking score of an item only based on its relevance property, and the personalized user demands in terms of different learning objectives, such as diversity, tail novelty or recency, which have been played essential roles in multi-objective recommendation (MOR), are often neglected in SR. In this paper, we first discuss the importance of considering multiple different objectives within a learning model for recommender system. Next, to capture users' objective-level preferences by utilizing interactive information in the sequential context, we propose a novel Dynamic Multi-objective Recommendation (DMORec) framework with interactive evolution for SR. In particular, DMORec formulates a dynamic multi-objective optimization task to simultaneously optimize more than two varying objectives in an interactive recommendation process. Moreover, to resolve this optimization task in SR, we develop an evolutionary algorithm with supervised learning approach to obtain the Pareto-optimal solutions of the formulated problem. Comprehensive experiments on four real-world datasets demonstrate the effectiveness of the proposed DMORec for dynamic multi-objective recommendation in sequential recommender systems. This work was supported in part by joint project JD User Growth Engine under Grant H20211431, in part by the National Natural Science Foundation of China under Grant 61871272, in part by Shenzhen Fundamental Research Program under Grant JCYJ20190808173617147, in part by the Open Project of BGIShenzhen under Grant BGIRSZ20200002, and in part by the Venture and Innovation Support Program for Chongqing Overseas Returnees under Grants cx2018044 and cx2019020. 2023-09-11T02:05:59Z 2023-09-11T02:05:59Z 2023 Journal Article Zhou, W., Liu, Y., Li, M., Wang, Y., Shen, Z., Feng, L. & Zhu, Z. (2023). Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation. IEEE Transactions On Emerging Topics in Computational Intelligence, 7(4), 1228-1241. https://dx.doi.org/10.1109/TETCI.2023.3251352 2471-285X https://hdl.handle.net/10356/170379 10.1109/TETCI.2023.3251352 2-s2.0-85151341410 4 7 1228 1241 en IEEE Transactions on Emerging Topics in Computational Intelligence © 2023 IEEE. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Dynamic Multi-Objective Optimization Multi-Objective Recommendation Zhou, Wei Liu, Yong Li, Min Wang, Yu Shen, Zhiqi Feng, Liang Zhu, Zexuan Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation |
| title | Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation |
| title_full | Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation |
| title_fullStr | Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation |
| title_full_unstemmed | Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation |
| title_short | Dynamic multi-objective optimization framework with interactive evolution for sequential recommendation |
| title_sort | dynamic multi objective optimization framework with interactive evolution for sequential recommendation |
| topic | Engineering::Computer science and engineering Dynamic Multi-Objective Optimization Multi-Objective Recommendation |
| url | https://hdl.handle.net/10356/170379 |
| work_keys_str_mv | AT zhouwei dynamicmultiobjectiveoptimizationframeworkwithinteractiveevolutionforsequentialrecommendation AT liuyong dynamicmultiobjectiveoptimizationframeworkwithinteractiveevolutionforsequentialrecommendation AT limin dynamicmultiobjectiveoptimizationframeworkwithinteractiveevolutionforsequentialrecommendation AT wangyu dynamicmultiobjectiveoptimizationframeworkwithinteractiveevolutionforsequentialrecommendation AT shenzhiqi dynamicmultiobjectiveoptimizationframeworkwithinteractiveevolutionforsequentialrecommendation AT fengliang dynamicmultiobjectiveoptimizationframeworkwithinteractiveevolutionforsequentialrecommendation AT zhuzexuan dynamicmultiobjectiveoptimizationframeworkwithinteractiveevolutionforsequentialrecommendation |