Jianfei Cui
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jianfei Cui has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Feng Zhang
Bytedance, Beijing, China
2 shared publications - Xingyan Bin
ByteDance Inc., Beijing, China
2 shared publications - Zhichen Zhao
ByteDance Inc., Beijing, China
2 shared publications - Zuotao Liu
ByteDance, Shanghai, China
2 shared publications - Chongyang Yan
ByteDance Inc., Beijing, China
1 shared publication - Jing Yan
Bytedance, Singapore, Singapore
1 shared publication
Latest Publications
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4273-4283
Real-time Indexing for Large-scale Recommendation by Streaming Vector Quantization Retriever
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4273-4283
Open AccessReal-time Indexing for Large-scale Recommendation by Streaming Vector Quantization Retriever
- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 6095-6104
Trinity: Syncretizing Multi-/Long-Tail/Long-Term Interests All in One
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 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. 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.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 6095-6104
Open AccessTrinity: Syncretizing Multi-/Long-Tail/Long-Term Interests All in One
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 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. 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.