4 papers
Stratified Expert Cloning for Retention-Aware Recommendation at Scale
Chengzhi Lin, Annan Xie, Shuchang Liu +3
User retention is critical in large-scale recommender systems, significantly influencing online platforms' long-term success. Existing methods typically focus on short-term engagem…
Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation
Chengzhi Lin, Shuchang Liu, Chuyuan Wang +1
Accurately predicting watch time is crucial for optimizing recommendations and user experience in short video platforms. However, existing methods that estimate a single average wa…
AlignPxtr: Aligning Predicted Behavior Distributions for Bias-Free Video Recommendations
Chengzhi Lin, Chuyuan Wang, Annan Xie +5
In video recommendation systems, user behaviors such as watch time, likes, and follows are commonly used to infer user interest. However, these behaviors are influenced by various…
Dreaming User Multimodal Representation Guided by The Platonic Representation Hypothesis for Micro-Video Recommendation
Chengzhi Lin, Hezheng Lin, Shuchang Liu +5
The proliferation of online micro-video platforms has underscored the necessity for advanced recommender systems to mitigate information overload and deliver tailored content. Desp…