Open-World Spatio-Temporal Graph Neural Networks for Dynamic Modeling of Urban Networks

Summary
Today, thanks to the rapid developing mobile and sensor networks in IoT (Internet of Things) systems, spatio-temporal big data are being constantly generated. They have brought us a data-driven possibility to understand and model network dynamics on a city scale. A fundamental task towards the next-generation mobility services, such as Intelligent Transportation Systems (ITS), Mobility-as-a-Service (MaaS), is spatio-temporal predictive modeling of the geo-sensory signals. There is a recent line of research leveraging graph neural networks (GNN) to boost the forecasting performance on such tasks. While simulating the regularity of mobility behaviors in a more sophisticated way, the existing studies ignore the open-world property of urban networks. There are various events (e.g., holidays, extreme weathers, pandemic, accidents) occurring from time to time cause non-stationary phenomena on networks, which by nature make the spatio-temporal forecasting task challenging. We thereby propose an open-world spatio-temporal graph neural networks that is capable of fast adapting and making robust predictions in different scenarios, which is crucial to decision making towards emergency response and urban resilience. This seminar series is co-organized by CHUD (Center for Housing & Urban Development), GeoSAT (Center for Geospatial Sciences, Applications and Technology), and TAMIDS-DAL (Design and Analytics Lab for Urban Artificial Intelligence @ Texas A&M Institute of Data Science).

Speaker’s information
Dr. Zhaonan Wang is currently a Postdoctoral Research Associate at the Department of Geography and Geographic Information Science, University of Illinois Urbana-Champaign. He received his Ph.D. degree in Environmental Sciences from The University of Tokyo in 2022. Before, he received his B.S. and M.A. degrees in Geographic Information Systems and City Planning from Peking University and Boston University respectively. Dr. Wang’s research focuses on interdisciplinary applications of AI on geospatial and spatio-temporal data in solving urban and societal challenges. He has been publishing papers and serving as Program Committee members at top-tier AI and data science venues, such as AAAI, KDD, WWW, CIKM, ICDE. He was also a receiver of the prestigious MEXT (Japanese Government) scholarship during Ph.D. program.

Time: 10:00-10:30 a.m. US Central Time (Thursday, April 6, 2023)
Zoom Meeting ID: 972 3088 4329 Passcode: 655335
Direct Link: https://tamu.zoom.us/j/97230884329?pwd=ZTU0Y0hPTGQ2dmpNVG5zOHB2QURGUT09

Host: Jiaxin Du, Data Science Ambassador@TAMIDS, PhD candidate@LAUP, TAMU