HKUST GeoAI Workshop
GeoAI is a recent hot topic which is interdisciplinary. It combines the technology of AI in the field of geo-spatial database.
The purpose of this workshop is to bring top researchers in the research field to the UST campus.
University members could benefit from the workshop by attending the workshop to learn from the talks and the panel discussion from speakers in the workshop.
Keynote 1: Re-configuring Data Practices for Intelligent, Reliable and Responsible Spatial Decision-making Systems
Speaker: Timos Sellis (Athena Research Center)
Time: 09:40 am - 10:40 am
Abstract: In this talk we will focus on how spatial data management practices need to be re-configured in order to support Intelligent, Reliable and Responsible spatial decision-making systems. The appetite for effective use of information assets has been steadily rising in both public and private sector organisations. However, whether the information is used for social good or commercial gain, there is a growing recognition of the complex socio-technical challenges associated with balancing the diverse demands of regulatory compliance and data privacy, social expectations and ethical use, business process agility and value creation, and scarcity of data science talent. In this talk, we highlight these interconnected challenges and introduce how requirements of responsible and agile approaches to information use can be positioned. The aim is to develop and present methodologies that can serve as a reference for future research and development in relevant areas of Responsible Spatial Data Management.
Keynote 2: Location & Privacy: Past, Present and Future -A GeoAI Perspective
Speaker: Cyrus Shahabi (University of Southern California)
Time: 11:10 am - 12:10 pm
Abstract: In this talk, I will review various types of mobile applications, from Location-Based-Services (LBS) and Ride-Sharing to pandemic risk-prediction applications, which collect, analyze and use location data to provide various services to users. I explain some of the main underlying technologies (e.g., kNN queries and contact-network analysis) that enable these applications from a spatial data management and analysis (aka GeoAI) perspective. I will also discuss some of the privacy concerns with these applications due to their location leaks and review several approaches to protect location privacy without sacrificing the utility of these applications. I will wrap up by presenting some new envisioned applications and their corresponding open problems.
Keynote 3: Trustworthy and Collaborative AI through Federated Learning
Speaker: Li Xiong (Emory University)
Time: 02:00 pm - 03:00 pm
Abstract: Federated learning (FL) is a driving technology for collaborative AI which allows decentralized clients (e.g., edge devices or healthcare organizations) to collaboratively train machine learning models without directly sharing their data. I will present several of our recent works towards trustworthy FL including: 1) addressing data heterogeneity across clients, 2) ensuring formal privacy of the final model while optimizing model utility, and 3) ensuring robustness against potential failures and attacks of the clients. I will discuss several applications for harnessing decentralized health and mobility data for public health and healthcare (including our recent effort in supporting the 2023 US-UK privacy enhancing technology challenge for pandemic) and conclude with open research questions.
Local Talk 2: Towards Large-Scale Spatiotemporal Kernel Density Visualization
Speaker: Jianliang Xu (Hong Kong Baptist University)
Time: 03:00 pm - 03:30 pm
Abstract: Kernel Density Visualization (KDV) is a widely used technique in disciplines such as geography, crime science, transportation science, and ecology for analyzing geospatial data. However, the scalability of KDV methods has become a concern due to limitations in existing software tools when dealing with massive geospatial datasets and generating high-resolution KDVs. In this talk, we will discuss the challenges associated with scalability in KDV and present our recent efforts in developing efficient algorithms to address these challenges.
Bigography: Jianliang Xu is the Head and Chair Professor of the Department of Computer Science at Hong Kong Baptist University. His current research interests include big data management, data security & privacy, and blockchain technology. With an h-index of 56, he has published more than 250 technical papers in these areas, most of which have appeared in leading journals and conferences, including SIGMOD, PVLDB, ICDE, TKDE, and VLDBJ. He is listed among the world's top 2% scientists by Stanford University. He has served as a Program Committee Co-Chair for a number of international conferences and as an Associate Editor for several top-tier international journals including TKDE and PVLDB. More details can be found at: https://www.comp.hkbu.edu.hk/~xujl/.
Local Talk 3: Mobility Data Science for Social Goods
Speaker: Reynold Cheng (The University of Hong Kong)
Time: 04:00 pm - 04:30 pm
Abstract: In recent years, there is a huge increase in the use of mobility data science and AI for addressing a wide range of important social domains. In this talk, I will discuss how the HKU STAR (Social Technology And Research) Lab uses mobility data science technologies for analysing the traveling patterns of passengers during the COVID pandemic. We examine the role that transportation plays in the spread of COVID-19. For example, how does the pandemic affect the anxiety and the choices of the passengers? How are travel patterns affected by the shutdown of a railway station? Answering these questions can lead to a better understanding of the interaction between transportation and coronavirus spread, so as to make us more aware of the infection risks in different transportation tools, and help policy makers to make better prevention and control strategies. I will discuss the recent progress of addressing the above problems, with a data-driven approach on the traveling records of the Hong Kong Mass Transit Railway (MTR) passengers. I will also talk about my recent effort in using mobility data technologies for enhancing service quality and streamlining administrative work of social workers from 14 NGOs, supporting more than 7,000 users. The STAR lab's effort has been recognised by an HKICT Award, two Asia Smart App Awards, and an HKU Faculty Knowledge Exchange Award.
Panel Discussion: GeoAI: Past, Present and Future
Panel Members: Timos Sellis (Athena Research Center), Cyrus Shahabi (University of Southern California), Li Xiong (Emory University)
Moderator: Raymond Chi-Wing Wong (The Hong Kong University of Science and Technology)
Time: 04:30 pm - 06:00 pm
Abstract: This panel discussion involves our 3 oversea keynote speakers, namely Timos Sellis (Athena Research Center), Cyrus Shahabi (University of Southern California) and Li Xiong (Emory University), moderated by Raymond Chi-Wing Wong (The Hong Kong University of Science and Technology). Since they are experts in GeoAI, they will discuss the "past", the "present" and the "future" of GeoAI in this panel discussion. Interested participants could also ask questions in this panel discussion to obtain insights from our panelists.
Registration is free of charge. Please click here for registration.
RSVP and first-come-first-served
Registration deadline: 22 September 2023.