Kun Gai
14 papers in the PaperMetrix corpus
Papers by this author
-
Two-Stage Constrained Actor-Critic for Short Video Recommendation
2023
The wide popularity of short videos on social media poses new opportunities and challenges to optimize recommender systems on the video-sharing platforms. Users sequentially interact with the system and provide complex and multi-faceted responses, including …
-
Mixed Attention Network for Cross-domain Sequential Recommendation
2023 · arXiv (Cornell University)
In modern recommender systems, sequential recommendation leverages chronological user behaviors to make effective next-item suggestions, which suffers from data sparsity issues, especially for new users. One promising line of work is the cross-domain recommendation, which …
-
HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou
2024 · arXiv (Cornell University)
In this paper, we present the practical problems and the lessons learned at short-video services from Kuaishou. In industry, a widely-used multi-task framework is the Mixture-of-Experts (MoE) paradigm, which always introduces some shared and specific …
-
RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems
2024
Modern recommender systems are built upon computation-intensive infrastructure, and it is challenging to perform real-time computation for each request, especially in peak periods, due to the limited computational resources. Recommending by user-wise result caches is …
-
A Multi-modal Modeling Framework for Cold-start Short-video Recommendation
2024
Short video has witnessed rapid growth in the past few years in multimedia platforms. To ensure the freshness of the videos, platforms receive a large number of user-uploaded videos every day, making collaborative filtering-based recommender …
-
Missing Interest Modeling with Lifelong User Behavior Data for Retrieval Recommendation
2024
Rich user behavior data has been proven to be of great value for recommendation systems. Modeling lifelong user behavior data in the retrieval stage to explore user long-term preference and obtain comprehensive retrieval results is …
-
LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application
2025 · Proceedings of the AAAI Conference on Artificial Intelligence
Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items. However, this approach overlooks the wealth of semantic information embedded within textual descriptions of items, leading to suboptimal performance …
-
CHIME: A Compressive Framework for Holistic Interest Modeling
2025 · arXiv (Cornell University)
Modeling holistic user interests is important for improving recommendation systems but is challenged by high computational cost and difficulty in handling diverse information with full behavior context. Existing search-based methods might lose critical signals during …
-
Learning Tree-based Deep Model for Recommender Systems
2018
Model-based methods for recommender systems have been studied extensively in recent years. In systems with large corpus, however, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full …
-
Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
2019
User response prediction, which models the user preference w.r.t. the presented items, plays a key role in online services. With two-decade rapid development, nowadays the cumulated user behavior sequences on mature Internet service platforms have …
-
Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction
2019
Click-through rate (CTR) prediction is critical for industrial applications such as recommender system and online advertising. Practically, it plays an important role for CTR modeling in these applications by mining user interest from rich historical …
-
Deep Interest Evolution Network for Click-Through Rate Prediction
2019 · Proceedings of the AAAI Conference on Artificial Intelligence
Click-through rate (CTR) prediction, whose goal is to estimate the probability of a user clicking on the item, has become one of the core tasks in the advertising system. For CTR prediction model, it is …
-
Entire Space Multi-Task Model
2018
Estimating post-click conversion rate (CVR) accurately is crucial for ranking systems in industrial applications such as recommendation and advertising. Conventional CVR modeling applies popular deep learning methods and achieves state-of-the-art performance. However it encounters several …
-
Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
2020
Rich user behavior data has been proven to be of great value for click-through rate prediction tasks, especially in industrial applications such as recommender systems and online advertising. Both industry and academy have paid much …