H
Han Li
Researcher at Alibaba Group
Publications - 31
Citations - 2334
Han Li is an academic researcher from Alibaba Group. The author has contributed to research in topics: Reinforcement learning & Tree (data structure). The author has an hindex of 13, co-authored 31 publications receiving 1283 citations. Previous affiliations of Han Li include Tsinghua University.
Papers
More filters
Proceedings ArticleDOI
Deep Interest Network for Click-Through Rate Prediction
Guorui Zhou,Xiaoqiang Zhu,Chenru Song,Ying Fan,Han Zhu,Xiao Ma,Yan Yanghui,Junqi Jin,Han Li,Kun Gai +9 more
TL;DR: A novel model: Deep Interest Network (DIN) is proposed which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad.
Proceedings ArticleDOI
Learning Tree-based Deep Model for Recommender Systems
TL;DR: Wang et al. as mentioned in this paper proposed a novel tree-based method which can provide logarithmic complexity w.r.t. corpus size even with more expressive models such as deep neural networks.
Proceedings ArticleDOI
Learning Tree-based Deep Model for Recommender Systems
TL;DR: A novel tree-based method which can provide logarithmic complexity w.r.t. corpus size even with more expressive models such as deep neural networks is proposed and can be jointly learnt towards better compatibility with users' interest distribution and hence facilitate both training and prediction.
Proceedings ArticleDOI
Real-Time Bidding with Multi-Agent Reinforcement Learning in Display Advertising
TL;DR: The results show cluster-based bidding would largely outperform single-agent and bandit approaches, and the coordinated bidding achieves better overall objectives than purely self-interested bidding agents.
Proceedings ArticleDOI
Optimized Cost per Click in Taobao Display Advertising
TL;DR: A bid optimizing strategy called optimized cost per click (OCPC) is proposed which automatically adjusts the bid to achieve finer matching of bid and traffic quality of page view (PV) request granularity and yields substantially better results than previous fixed bid manner.