Reinforcing User Interest Evolution in Multi-Scenario Learning for recommender systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912443903508480 |
|---|---|
| author | Feng, Zhijian Zheng, Wenhao Xiao, Xuanji |
| author_facet | Feng, Zhijian Zheng, Wenhao Xiao, Xuanji |
| contents | In real-world recommendation systems, users would engage in variety scenarios, such as homepages, search pages, and related recommendation pages. Each of these scenarios would reflect different aspects users focus on. However, the user interests may be inconsistent in different scenarios, due to differences in decision-making processes and preference expression. This variability complicates unified modeling, making multi-scenario learning a significant challenge. To address this, we propose a novel reinforcement learning approach that models user preferences across scenarios by modeling user interest evolution across multiple scenarios. Our method employs Double Q-learning to enhance next-item prediction accuracy and optimizes contrastive learning loss using Q-value to make model performance better. Experimental results demonstrate that our approach surpasses state-of-the-art methods in multi-scenario recommendation tasks. Our work offers a fresh perspective on multi-scenario modeling and highlights promising directions for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_17682 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Reinforcing User Interest Evolution in Multi-Scenario Learning for recommender systems Feng, Zhijian Zheng, Wenhao Xiao, Xuanji Information Retrieval Artificial Intelligence 68T07 H.3.3 In real-world recommendation systems, users would engage in variety scenarios, such as homepages, search pages, and related recommendation pages. Each of these scenarios would reflect different aspects users focus on. However, the user interests may be inconsistent in different scenarios, due to differences in decision-making processes and preference expression. This variability complicates unified modeling, making multi-scenario learning a significant challenge. To address this, we propose a novel reinforcement learning approach that models user preferences across scenarios by modeling user interest evolution across multiple scenarios. Our method employs Double Q-learning to enhance next-item prediction accuracy and optimizes contrastive learning loss using Q-value to make model performance better. Experimental results demonstrate that our approach surpasses state-of-the-art methods in multi-scenario recommendation tasks. Our work offers a fresh perspective on multi-scenario modeling and highlights promising directions for future research. |
| title | Reinforcing User Interest Evolution in Multi-Scenario Learning for recommender systems |
| topic | Information Retrieval Artificial Intelligence 68T07 H.3.3 |
| url | https://arxiv.org/abs/2506.17682 |