Q
Qiwei Chen
Researcher at Alibaba Group
Publications - 8
Citations - 596
Qiwei Chen is an academic researcher from Alibaba Group. The author has contributed to research in topics: Computer science & Recommender system. The author has an hindex of 4, co-authored 5 publications receiving 224 citations.
Papers
More filters
Proceedings ArticleDOI
Behavior sequence transformer for e-commerce recommendation in Alibaba
TL;DR: This paper proposes to use the powerful Transformer model to capture the sequential signals underlying users' behavior sequences for recommendation in Alibaba and demonstrates the superiority of the proposed model.
Posted Content
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
Chao Li,Zhiyuan Liu,Mengmeng Wu,Yuchi Xu,Pipei Huang,Huan Zhao,Guoliang Kang,Qiwei Chen,Wei Li,Dik Lun Lee +9 more
TL;DR: This paper designs a multi-interest extractor layer based on the recently proposed dynamic routing mechanism, which is applicable for modeling and extracting diverse interests from user's behaviors, and proposes a technique named label-aware attention to help the learning process of user representations.
Proceedings ArticleDOI
Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
Chao Li,Zhiyuan Liu,Mengmeng Wu,Yuchi Xu,Huan Zhao,Pipei Huang,Guoliang Kang,Qiwei Chen,Wei Li,Dik Lun Lee +9 more
TL;DR: In this article, a multi-interest extractor layer based on the recently proposed dynamic routing mechanism is proposed for modeling and extracting diverse interests from user's behaviors, and a technique named label-aware attention is proposed to help the learning process of user representations.
Posted Content
Behavior Sequence Transformer for E-commerce Recommendation in Alibaba
TL;DR: Wang et al. as discussed by the authors proposed to use the Transformer model to capture the sequential signals underlying users' behavior sequences for recommendation in Alibaba, which obtained significant improvements in online Click-Through-Rate (CTR) comparing to two baselines.
Journal ArticleDOI
Efficient Long Sequential User Data Modeling for Click-Through Rate Prediction
TL;DR: This paper proposes an end-to-end paradigm to model long behavior sequences, which is able to achieve superior performance along with remarkable cost-efficiency compared to existing models, and proposes a hashing-based efficient target attention (TA) network named ETA-Net, which can reduce the complexity of standard TA by orders of magnitude for sequential data modeling.