J
Jian Wu
Researcher at Alibaba Group
Publications - 8
Citations - 1213
Jian Wu is an academic researcher from Alibaba Group. The author has contributed to research in topics: Ranking & Recommender system. The author has an hindex of 4, co-authored 7 publications receiving 443 citations.
Papers
More filters
Proceedings ArticleDOI
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
TL;DR: BERT4Rec as discussed by the authors employs the deep bidirectional self-attention to model user behavior sequences, predicting the random masked items in the sequence by jointly conditioning on their left and right context.
Posted Content
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
TL;DR: A sequential recommendation model called BERT4Rec is proposed, which employs the deep bidirectional self-attention to model user behavior sequences, and outperforms various state-of-the-art sequential models consistently.
Proceedings ArticleDOI
Personalized re-ranking for recommendation
Changhua Pei,Yi Zhang,Yongfeng Zhang,Fei Sun,Xiao Lin,Hanxiao Sun,Jian Wu,Peng Jiang,Junfeng Ge,Wenwu Ou,Dan Pei +10 more
TL;DR: The proposed re-ranking model can be easily deployed as a follow-up modular after any ranking algorithm, by directly using the existing ranking feature vectors and directly optimizes the whole recommendation list by employing a transformer structure to efficiently encode the information of all items in the list.
Proceedings ArticleDOI
Privileged Features Distillation at Taobao Recommendations
Chen Xu,Quan Li,Junfeng Ge,Jinyang Gao,Xiaoyong Yang,Changhua Pei,Fei Sun,Jian Wu,Hanxiao Sun,Wenwu Ou +9 more
TL;DR: Zhang et al. as discussed by the authors proposed privileged features distillation (PFD) to bridge the gap between training and inference for e-commerce recommendation, where the learned discriminative features are transferred from the more accurate teacher model to the student model, which helps to improve its prediction accuracy.
Posted Content
Personalized Re-ranking for Recommendation
Changhua Pei,Yi Zhang,Yongfeng Zhang,Fei Sun,Xiao Lin,Hanxiao Sun,Jian Wu,Peng Jiang,Wenwu Ou +8 more
TL;DR: Zhang et al. as discussed by the authors proposed a personalized re-ranking model for recommender systems, which directly optimizes the whole recommendation list by employing a transformer structure to efficiently encode the information of all items in the list.