About Me
I am currently a senior algorithm engineer in Alimama, which is the advertising department of Alibaba Group. I received my master degree from the College of Computer Science and Technology, Zhejiang University, and was co-advised by Yang Yang and Fei Wu in Digital media Computing & Design Lab. I also fortunately had Chenhao Tan from University of Colorado Boulder as my external advisor.
My research focuses on urban computing with heterogeneous data sources:
- Migrant integration in urbanization: The unprecedented large-scale migration poses both significant challenges for policymakers and important questions for researchers. To understand the process of migrant integration, we employ a user telecommunication metadata in Shanghai and study systematic differences between locals and migrants in their mobile communication networks and geographical locations, and demonstrate the integration process of new migrants. (Yang et al., AAAI'18)
- Early departure of new migrants: In the rapid urbanization process, many of migrants fail to settle down and eventually leave the city. To examine the disintegration process for some migrants who left early, we employ a novel dataset combining user telecommunication metadata and housing price, and investigate migrants’ behavior in their first weeks. At last, we formulate a churn prediction problem to determine whether a migrant is going to leave based on his/her behavior in the first few days.(Yang et al., WWW'18)
- Imputation for residents' power usage: Different time series data (e.g., power usage, real-time voltage) is measured in residents' daily life. A common challenge for using such data for mining people's behaviorial patterns is the imputation of the missing values with reasonable ones. We study the social-aware time series imputation problem and propose a sequential encoder-decoder-based imputation framework with an attention mechanism combining social context and temporal context. (Liu et al., WWW'19)
Selected Works
- Zongtao Liu, Bin Ma, Quan Liu, Jian Xu, Bo Zheng. Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matching. In Proceedings of the 30th Conference on Information and Knowledge Management (CIKM'21), 2021. [PDF]
- Jiarong Xu, Yang Yang, Chunping Wang, Zongtao Liu, Jing Zhang, Lei Chen and Jiangang Lu. Robust Network Enhancement from Flawed Networks. In IEEE Transaction on Knowledge and Data Engineering(TKDE), 2020. [PDF]
- Zongtao Liu, Yang Yang, Wei Huang, Zhongyi Tang, Ning Li and Fei Wu. How Do Your Neighbors Disclose Your Information: Social-Aware Time Series Imputation. In Proceedings of the 28th World Wide Web Conference (WWW'19), 2019. [PDF]
- Yang Yang, Zongtao Liu, Chenhao Tan, Fei Wu, Yueting Zhuang, and Yafeng Li. To Stay or to Leave: Churn Prediction for Urban Migrants in the Initial Period. In Proceedings of the 27th World Wide Web Conference (WWW'18), 2018, pages 967-976. [PDF] [Slides] [Data]
- Yang Yang, Chenhao Tan, Zongtao Liu, Fei Wu, and Yueting Zhuang. Urban Dreams of Migrants: A Case Study of Migrant Integration in Shanghai. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence (AAAI'18), 2018, pages 507-514. [PDF]
Selected Awards
- 2019, awarded National Scholarship(Top 1%)
- 2018, awarded Vmware Excellent Student Scholarship(Top 5%)
Contact Me
Email: tomstream@zju.edu.cn
Wechat: tomstream2013