Name: Hongning Wang
Title: Associate Professor
Email: hw-ai@tsinghua.edu.cn
Homepage: https://www.cs.virginia.edu/~hw5x/
Education
Ph.D. (Computer Science), University of Illinois at Urbana-Champaign, USA, 2014
M.E. (Computer Science and Technology), Tsinghua University, China, 2009
B.E. (Computer Science and Technology), Tsinghua University, China,
2007
Employment
September 2023 - Present: Tenured Associate Professor, Department of Computer Science, Tsinghua University
December 2022 - August 2023: Copenhaver Endowed Associate Professor, University of Virginia, USA
August 2020 - November 2022: Tenured Associate Professor, University of Virginia, USA
August 2014 - July 2020: Tenure-Track Assistant Professor, University of Virginia, USA
Professional Service
ACM Transactions on Intelligent Systems and Technology (TIST), Associate Editor （2022 to date）
Frontiers in Big Data，Associate Editor （2021 to date）
ACM SIGIR Conference on Research and Development in Information Retrieval, Co-General Chair （2024）
ACM SIGKDD Conference On Knowledge Discovery And Data Mining, Workshop Co-Chair（2022，2023）
AAAI Conference on Artificial Intelligence, Area Chair（2022 to date）
International Joint Conferences on Artificial Intelligence, Area Chair (2023)
ACM SIGKDD Conference On Knowledge Discovery And Data Mining, Area Chair（2022 to date）
The Web Conference, Area Chair（2020 to date）
Research Areas
Machine learning, information retrieval, and data mining
Research Overview
My research focuses on developing machine learning methods with a strong theoretical foundation and practical performance to address real-world decision-making problems. In recent years, we have been conducting extensive research in interactive online learning, establishing theoretical frameworks and provable solutions for information retrieval and recommendation problems. Our theoretical and algorithmic contributions have been successfully applied in an array of real-world systems, including the recommendation system in KuaiShou and Instagram, and retrieval system in Google and Bing. Our research has created several novel techniques, including online learning to rank on top of deep neural networks, and user latent intent understanding and modeling based on latent variable probabilistic models. These methods have found successful applications in critical areas such as large-scale information retrieval and recommendation systems, online education, healthcare, information integration in IoT systems, thereby creating substantial societal value.
To date, our research has generated over 140 publications, with a primary focus on top-tier conferences in the field, such as NeurIPS, ICML, ICLR, KDD, and SIGIR. Our research has been recognized with numerous awards, including the Best Paper Award at SIGIR 2019, as well as nominations for the Best Paper Award at WWW 2021 and BuildSys 2018. We have received support from the United States National Science Foundation, including the CAREER award, the United States Department of Energy, and multiple collaborations with leading industry companies, such as Google, Meta and ByteDance.
Furthermore, several of our doctoral graduate students have become tenure-track assistant professors at renowned research universities in the United States. Two of them are affiliated with the College of Information Sciences and Technology at Pennsylvania State University, and one is in the Department of Electrical Engineering and Computer Science at Oregon State University. One of our postdoctoral researchers has also moved on to become a tenure-track assistant professor at the Indian Institute of Technology's Department of Computer Science.
Awards and Honors
Conference on Neural Information Processing Systems Top Reviewer，2022
International Conference on Learning Representations Outstanding Reviewer, 2021
Google Faculty Research Award,2020
Microsoft Research Faculty Fellowship Finalist，2020
ACM SIGIR Conference on Research and Development in Information Retrieval Best Paper Award, 2019
NSF Faculty Early Career Development Program (CAREER) Award, 2016
Selected Publications
1. Fan Yao, Chuanhao Li, Karthik Abinav Sankararaman, Yiming Liao, Yan Zhu, Qifan Wang and Hongning Wang, Haifeng Xu. Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial? Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS'2023), 2023.
2. Zhepei Wei, Chuanhao Li, Haifeng Xu and Hongning Wang. Incentivized Communication for Federated Bandits. Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS'2023), 2023.
3. Xiaoying Zhang, Junpu Chen, Hongning Wang, Hong Xie, Hang Li. Uncertainty-Aware Off-Policy Learning. Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS'2023), 2023.
4. Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang, Haifeng Xu. How Bad is Top-K Recommendation under Competing Content Creators? The Fortieth International Conference on Machine Learning (ICML'2023), Oral presentation, 2023.
5. Lu Lin, Jinghui Chen and Hongning Wang. Spectral Augmentation for Self-Supervised Learning on Graphs. The Tenth International Conference on Learning Representations (ICLR'2023), Spotlight presentation, 2023.
6. Chuanhao Li and Hongning Wang. Communication Efficient Federated Learning for Generalized Linear Bandits. Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS'2022), 2022.
7. Fan Yao, Chuanhao Li, Denis Nekipelov, Hongning Wang and Haifeng Xu. Learning from a Learning User for Optimal Recommendations. The Thirty-ninth International Conference on Machine Learning (ICML'2022), 2022.
8. Chuanhao Li and Hongning Wang. Asynchronous Upper Confidence Bound Algorithms for Federated Linear Bandits. The 25th International Conference on Artificial Intelligence and Statistics (AISTATS'2022), p6529-6553, 2022.
9. Yiling Jia, Huazheng Wang, Stephen Guo and Hongning Wang. PairRank: Online Pairwise Learning to Rank by Divide-and-Conquer. The Web Conference 2021 (WWW'2021), p146-157, 2021. Nominated for the Best Paper Award
10. Huazheng Wang, Sonwoo Kim, Eric McCord-Snook, Qingyun Wu and Hongning Wang. Variance Reduction in Gradient Exploration for Online Learning to Rank. The 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019), p835-844, 2019. Best Paper Award
A complete list of my publications can be found here：https://www.cs.virginia.edu/~hw5x/publications.html
