HGenPush: A Heterogeneous Generative Recommendation Architecture for Industrial Push Notification Systems
2026-07-03 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors created a new recommendation system called HGenPush to better suggest both videos and their authors to users on short-video platforms. Their system looks at different types of user behavior to understand what users like, and it generates recommendations more efficiently than older methods. They also use user feedback to make the recommendations better over time. When tested on a real platform, Kuaishou, their system helped increase daily active users slightly.
recommendation systemsshort-video platformsuser behavior analysisgenerative recommendationautoregressive modelsmulti-token predictionuser feedbackpush notification systemscontent personalization
Authors
Xiao Liang, Jiali Feng, Xin Feng, Yiqing Wang, Baolin Ye, Siyao Feng, Zhihui Deng, Cunyi Zhang, Huajin Sun, Xuanping Li, Kaiqiao Zhan, Yanan Niu, Kun Gai
Abstract
With the explosive growth of content platforms, recommendation systems need to better satisfy user demands to enhance user satisfaction and retention. Taking short-video platforms as an example, users not only seek high-quality content but also trusted authors. Although generative recommendation systems have achieved breakthroughs in recent years, existing methods primarily generate single-type recommendation content and typically employ the inefficient autoregressive paradigm to generate semantic IDs. In this paper, we propose an end-to-end heterogeneous generative recommendation architecture called HGenPush. First, we design a hybrid user behavior understanding module that integrates multi-scenario and multi-perspective behaviors to capture precise user interest. Then, we design a dual-branch heterogeneous generative recommendation module that integrates video recommendation and author recommendation within a unified framework. In addition, to improve generation efficiency, we design a lightweight multi-token prediction method that discards the autoregressive paradigm. Finally, we design a user consumption preference alignment module, which leverages user feedback as reward signals to guide the model toward generating higher-quality content, thereby enhancing user experience and engagement. Through these designs, HGenPush simultaneously fulfills users' demands for high-quality content and trusted authors. We have deployed HGenPush on the push notification system of Kuaishou, a large-scale short-video platform, achieving a significant 0.181% increase in daily active users.