Zhihui Yang (杨智慧)

Zhihui Yang (杨智慧)

Researcher | School of Software Technology | Zhejiang University

Email: zhyangcs@zju.edu.cn

About Me

Dr. Zhihui Yang is a researcher at the School of Software Technology, Zhejiang University. She is also a member of the Intelligent Service Committee of the Artificial Intelligence Society. She received her Ph.D. degree in Computer Science from Fudan Unviersity in Jan. 2022, under the supervision of Prof. X. Sean Wang. She was a Visiting Scholar at the Information Systems Group (ISG) at UC Irvine from Sep. 2018 to Sep. 2020, mentored by Prof. Chen Li and Dr. Yao Lu. She served as a senior researcher at Zhejiang Lab from Feb. 2022 to Feb. 2024. My CV is here.

My research interests are in the field of big data management and analytics, including database, query processing and optimization, database systems + machine learning (DB+ML).

News

  • I am looking for Highly Self-Motivated Students with a strong interest in Big Data Management and Analytics.
  • If you are interested in working with me, please send me an email with your CV and transcript.

Selected Publication

  1. Zhenyu Li, Zhihui Yang*, Kuan Lu, Jiahao Wang, Gongsheng Yuan, Sai Wu. “Adda: An Agent-Driven in-Database Feature Generation System.” In SIGMOD, 2026.
  2. Chenning Wu , Chang Lu , Yinan Jing, Zhenying He , Zhihui Yang, and X.Sean Wang. “GeoPhrase Tree: An Efficient Index for Frequent Phrase Query over Spatio-Temporal Ranges.” In Dasfaa, 2026.
  3. Kuan Lu, Zhihui Yang*, Sai Wu*, Ruichen Xia, Dongxiang Zhang, Gang Chen. “Adda: Towards Efficient in-Database Feature Generation via LLM-based Agents.” International Conference on Management of Data (SIGMOD), 2025. (Accepted).
  4. Yongshu Bai, Zhihui Yang, Feng Gao. “FAAST: An Efficient Serverless Framework Made Snapshot-based Function Response Fast.” The ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC), 174-185, 2024.
  5. Tianhuan Yu, Zhenying He, Zhihui Yang, Fei Ye, Yuankai Fan, Yinan Jing, Kai Zhang, X. Sean Wang. “Zebra: A Novel Method for Optimizing Text Classification Query in Overload Scenario.” World Wide Web Journal (WWWJ), 26(3): 905-931, 2023.
  6. Zhihui Yang, Zuozhi Wang, Yicong Huang, Yao Lu, Chen Li, X. Sean Wang. “Optimizing Machine Learning Inference Queries with Correlative Proxy Models.” Proceedings of the VLDB Endowment (PVLDB), 15(10): 2032 - 2044, 2022.
  7. Zhihui Yang, Yicong Huang, Zuozhi Wang, Feng Gao, Yao Lu, Chen Li, X. Sean Wang. “Demonstration of Accelerating Machine Learning Inference Queries with Correlative Proxy Models.” Proceedings of the VLDB Endowment (PVLDB), 15(12): 3734 - 3737, 2022.
  8. Lei Guan, Zhihui Yang, Dongshen Li, Xicheng Lu. “pdlADMM: An ADMM-based Framework for Parallel Deep Learning Training with Efficiency.” Neurocomputing, 435: 264 - 273, 2021.
  9. Lei Guan, Tao Sun, Linbo Qiao, Zhihui Yang, Dongsheng, Li, Keshi Ge, Xicheng Lu. “An Efficient parallel and distributed solution to nonconvex penalized linear SVMs.” Frontiers of Information Technology & Electronic Engineering. 21(4), 587 - 603, 2020.
  10. Huixin Ma, Zhihui Yang, Yinan Jing, Zhenying He, X. Sean Wang. “Answering Unique Topic Queries with Dynamic Threshold.” World Wide Web Journal (WWWJ), 22(1), 39 - 58, 2019.
  11. Zhihui Yang*, Huixin Ma, Zhenying He, X. Sean Wang. “Finding Maximal Ranges with Unique Topics in a Text Database.” World Wide Web Journal (WWWJ), 21(2), 289-310, 2018.
  12. Zhihui Yang, Jiyang Gong, Chaoying Liu, Yinan Jing, Zhenying He, Kai Zhang, X. Sean Wang. “iExplore: Accelerating Exploratory Data Analysis by Predicting User Intention.” In International conference on database systems for advanced application (DASFAA), 149 - 165, 2018.
  13. Lvhong Liu, Zhihui Yang, Zhenying He, Yinan Jing, Xiaoyang Sean Wang. “Unique Topic Query Processing on Cloud.” In IEEE International Conference on Cyber Security and Cloud Computing (CSCloud/EdgeCom), 103-105, 2018.
  14. 周凯文，杨智慧，马会心，何震瀛，荆一楠，王晓阳. “面向特定划分的主题模型的设计与实现.” 计算机科学与探索. 2017.
  15. 刘履宏，杨智慧，何震瀛，荆一楠，王晓阳，葛鹏程，孙超. “基于关系型信息抽取的独特主题查询系统.” NDBC. 2017.

Patents

  1. 王嘉豪，杨智慧，伍赛，陈刚. 一种查询计划结果数据集快速生成方法. CN 121188092 B
  2. 周新杰，杨智慧，伍赛，姚畅，汪睿，唐秀，袁巩生. 一种输入数据的隐私保护方法、装置、设备和存储介质. CN 120145457 B
  3. 王嘉豪，杨智慧，伍赛，姚畅，汪睿，唐秀，袁巩生. 面向代理模型的推理查询重优化方法、装置、设备和介质. CN 119149588 B
  4. 李振涛，杨智慧，伍赛，陈刚，应华，国宝. 基于孪生网络的非结构化数据连接查询优化系统及方法. CN 120723958 B
  5. 高裕杰，杨智慧，伍赛，张东祥，陈刚. 一种通用的非结构化数据索引构建方法、装置及介质. CN 120653807 B
  6. 芦宽，杨智慧，伍赛，姚畅，陈刚. 多智能体代理的数据库内的机器学习特征生成方法. CN 119151016 B
  7. 赵俊博，陈刚，张东祥，胡天磊，伍赛，王皓波，杨智慧. 一种大模型处理表格数据的方法、装置及介质. CN 118245485 B
  8. 杨智慧，王晓阳. 一种基于代理模型近似处理的推理查询优化方法及装置. CN 202311107124.5
  9. 杨智慧，王晓阳. 一种基于代理模型重排技术的推理查询优化方法及装置. CN 202311107125.X
  10. 叶飞，杨智慧，沈筠霏，何震瀛，荆一楠，张凯，王晓阳. 物化视图查询方法、系统、设备及存储介质. CN 202310374028.0
  11. 周凯文，杨智慧，马会心，何震瀛，荆一楠，王晓阳. 一种基于特定划分的主题模型下的文档生成方法. CN 201710548431.5