Keynotes

Keynote Speakers

	Zhenhui (Jessie) Li Chief Scientist at Yunqi Academy of Engineering
Title: Computing with 21,280 Global Cities
Abstract: We find ourselves at the thrilling dawn of a data-driven research paradigm. Nevertheless, we tend to place excessive emphasis on methodologies and theories, while the significance of the data itself is often overlooked. In this presentation, I will reassess some classical city science theories by leveraging big open data. I hope to elaborate crucial role that big open data in shaping the field of science. And more importantly, I would like to share how computer scientists can facilitate cross-disciplinary researchers to scale up their research.
Bio: Dr. Zhenhui (Jessie) Li is the chief scientist at Yunqi Academy of Engineering, a non-profit organization located in Hangzhou China. Previously, she held a tenured associate professorship at the Pennsylvania State University. Dr. Li has been dedicated to developing computational techniques for cross-disciplinary data-driven research, with a particular focus on applications in the city. Learn more about her on her website (https://jessielzh.com/).
	Chao Huang Assistant Professor at The University of Hong Kong
Title: Robust and Explainable Spatio-Temporal Graph Learning
Abstract: The growth of remote sensing technologies and large-scale computing infrastructure has led to an enormous collection of spatio-temporal data on an unprecedented scale across various fields such as transportation, environmental science, and public security. This diverse range of spatio-temporal data necessitates the integration of human-centered machine learning techniques with the rich spatio-temporal information available. In the era of big spatial-temporal data, the quantity of data being collected is often viewed as a source of high-quality information. However, the reality is more nuanced, as the effectiveness of data-driven methods is heavily dependent on the quality of the labeled training data available. Additionally, in urban computing applications, it is not sufficient to build accurate predictive solutions. Providing human-intelligible explanations is equally important, particularly for interdisciplinary domains. This presentation aims to introduce research that advances the analysis of large-scale spatio-temporal data towards robust, interpretable, and expressive spatial-temporal graph learning frameworks.
Bio: Chao Huang is an Assistant Professor at the Department of Computer Science in the University of Hong Kong (HKU). He is the director of Data Intelligence Lab@HKU, with the focus on developing novel machine learning frameworks to tackle various challenges in Data Mining, Information Retrieval, Spatial-Temporal Data Analytics, User Behavior Modeling, Recommendation, Graph Mining, Deep Representation Learning. Prior to that, he received my Ph.D. in Computer Science from the University of Notre Dame in USA.