Trinity: Syncretizing Multi-/Long-tail/Long-term Interests All in One
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913223147520000 |
|---|---|
| author | Yan, Jing Jiang, Liu Cui, Jianfei Zhao, Zhichen Bin, Xingyan Zhang, Feng Liu, Zuotao |
| author_facet | Yan, Jing Jiang, Liu Cui, Jianfei Zhao, Zhichen Bin, Xingyan Zhang, Feng Liu, Zuotao |
| contents | Interest modeling in recommender system has been a constant topic for improving user experience, and typical interest modeling tasks (e.g. multi-interest, long-tail interest and long-term interest) have been investigated in many existing works. However, most of them only consider one interest in isolation, while neglecting their interrelationships. In this paper, we argue that these tasks suffer from a common "interest amnesia" problem, and a solution exists to mitigate it simultaneously. We figure that long-term cues can be the cornerstone since they reveal multi-interest and clarify long-tail interest. Inspired by the observation, we propose a novel and unified framework in the retrieval stage, "Trinity", to solve interest amnesia problem and improve multiple interest modeling tasks. We construct a real-time clustering system that enables us to project items into enumerable clusters, and calculate statistical interest histograms over these clusters. Based on these histograms, Trinity recognizes underdelivered themes and remains stable when facing emerging hot topics. Trinity is more appropriate for large-scale industry scenarios because of its modest computational overheads. Its derived retrievers have been deployed on the recommender system of Douyin, significantly improving user experience and retention. We believe that such practical experience can be well generalized to other scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02842 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Trinity: Syncretizing Multi-/Long-tail/Long-term Interests All in One Yan, Jing Jiang, Liu Cui, Jianfei Zhao, Zhichen Bin, Xingyan Zhang, Feng Liu, Zuotao Information Retrieval Machine Learning Interest modeling in recommender system has been a constant topic for improving user experience, and typical interest modeling tasks (e.g. multi-interest, long-tail interest and long-term interest) have been investigated in many existing works. However, most of them only consider one interest in isolation, while neglecting their interrelationships. In this paper, we argue that these tasks suffer from a common "interest amnesia" problem, and a solution exists to mitigate it simultaneously. We figure that long-term cues can be the cornerstone since they reveal multi-interest and clarify long-tail interest. Inspired by the observation, we propose a novel and unified framework in the retrieval stage, "Trinity", to solve interest amnesia problem and improve multiple interest modeling tasks. We construct a real-time clustering system that enables us to project items into enumerable clusters, and calculate statistical interest histograms over these clusters. Based on these histograms, Trinity recognizes underdelivered themes and remains stable when facing emerging hot topics. Trinity is more appropriate for large-scale industry scenarios because of its modest computational overheads. Its derived retrievers have been deployed on the recommender system of Douyin, significantly improving user experience and retention. We believe that such practical experience can be well generalized to other scenarios. |
| title | Trinity: Syncretizing Multi-/Long-tail/Long-term Interests All in One |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2402.02842 |