An End-to-End Multi-objective Ensemble Ranking Framework for Video Recommendation
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_ | 1866908516251336704 |
|---|---|
| author | He, Tiantian Xie, Minzhi Li, Runtong Xu, Xiaoxiao Yu, Jiaqi Wang, Zixiu Hu, Lantao Li, Han Gai, Kun |
| author_facet | He, Tiantian Xie, Minzhi Li, Runtong Xu, Xiaoxiao Yu, Jiaqi Wang, Zixiu Hu, Lantao Li, Han Gai, Kun |
| contents | We propose a novel End-to-end Multi-objective Ensemble Ranking framework (EMER) for the multi-objective ensemble ranking module, which is the most critical component of the short video recommendation system. EMER enhances personalization by replacing manually-designed heuristic formulas with an end-to-end modeling paradigm. EMER introduces a meticulously designed loss function to address the fundamental challenge of defining effective supervision for ensemble ranking, where no single ground-truth signal can fully capture user satisfaction. Moreover, EMER introduces novel sample organization method and transformer-based network architecture to capture the comparative relationships among candidates, which are critical for effective ranking. Additionally, we have proposed an offline-online consistent evaluation system to enhance the efficiency of offline model optimization, which is an established yet persistent challenge within the multi-objective ranking domain in industry. Abundant empirical tests are conducted on a real industrial dataset, and the results well demonstrate the effectiveness of our proposed framework. In addition, our framework has been deployed in the primary scenarios of Kuaishou, a short video recommendation platform with hundreds of millions of daily active users, achieving a 1.39% increase in overall App Stay Time and a 0.196% increase in 7-day user Lifetime(LT7), which are substantial improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05093 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An End-to-End Multi-objective Ensemble Ranking Framework for Video Recommendation He, Tiantian Xie, Minzhi Li, Runtong Xu, Xiaoxiao Yu, Jiaqi Wang, Zixiu Hu, Lantao Li, Han Gai, Kun Information Retrieval We propose a novel End-to-end Multi-objective Ensemble Ranking framework (EMER) for the multi-objective ensemble ranking module, which is the most critical component of the short video recommendation system. EMER enhances personalization by replacing manually-designed heuristic formulas with an end-to-end modeling paradigm. EMER introduces a meticulously designed loss function to address the fundamental challenge of defining effective supervision for ensemble ranking, where no single ground-truth signal can fully capture user satisfaction. Moreover, EMER introduces novel sample organization method and transformer-based network architecture to capture the comparative relationships among candidates, which are critical for effective ranking. Additionally, we have proposed an offline-online consistent evaluation system to enhance the efficiency of offline model optimization, which is an established yet persistent challenge within the multi-objective ranking domain in industry. Abundant empirical tests are conducted on a real industrial dataset, and the results well demonstrate the effectiveness of our proposed framework. In addition, our framework has been deployed in the primary scenarios of Kuaishou, a short video recommendation platform with hundreds of millions of daily active users, achieving a 1.39% increase in overall App Stay Time and a 0.196% increase in 7-day user Lifetime(LT7), which are substantial improvements. |
| title | An End-to-End Multi-objective Ensemble Ranking Framework for Video Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2508.05093 |