Enhancing User Interest based on Stream Clustering and Memory Networks in Large-Scale Recommender Systems

Recommender Systems (RSs) provide personalized recommendation service based on user interest, which are widely used in various platforms. However, there are lots of users with sparse interest due to lacking consumption behaviors, which leads to poor recommendation results for them. This problem is widespread in large-scale RSs and is particularly difficult to address. To solve this challenging problem, we propose an innovative solution called User Interest Enhancement (UIE). UIE enhances user interest including user profile and user history behavior sequences by leveraging the enhancement vectors and personalized enhancement vectors generated based on dynamic streaming clustering of similar users and items from multiple perspectives, which are stored and updated in memory networks. UIE not only remarkably improves model performance for users with sparse interest, but also delivers notable gains for other users. As an end-to-end solution, UIE is easy to implement on top of existing ranking models. Furthermore, we extend our approach to long-tail items using similar methods, which also yields excellent improvements. We conduct extensive offline and online experiments in a large-scale industrial RS. The results demonstrate that our model substantially outperforms other existing approaches, especially for users with sparse interest. UIE has been deployed in several large-scale RSs at Tencent since 2022, which was made public on 21 May 2024. In addition, UIE-based methods have also been successfully applied in candidate generation, pre-ranking, and context-DNN stages. Multiple teams have developed solutions based on UIE, focusing primarily on updating clustering algorithms and attention mechanisms. As far as we know, UIE has been deployed by many companies. The thoughts of UIE, dynamic streaming clustering and similarity enhancement, have inspired subsequent relevant works.

@article{liu2025_2405.13238,
  title={ Enhancing User Interest based on Stream Clustering and Memory Networks in Large-Scale Recommender Systems },
  author={ Peng Liu and Nian Wang and Cong Xu and Ming Zhao and Bin Wang and Yi Ren },
  journal={arXiv preprint arXiv:2405.13238},
  year={ 2025 }
}