PRE-CONFERENCE EVENT TO THE WEB CONFERENCE 2021

Jure Leskovec

Stanford University

Mobility network models of COVID-19 explain inequities and inform reopening

The COVID-19 pandemic dramatically changed human mobility patterns, necessitating epidemiological models which capture the effects of changes in mobility on virus spread. In this talk we will introduce a metapopulation SEIR model that integrates fine-grained, dynamic mobility networks to simulate the spread of SARS-CoV-2 in 10 of the largest US metropolitan statistical areas. Derived from cell phone data, our mobility networks map the hourly movements of 98 million people from neighborhoods (census block groups, or CBGs) to points of interest (POIs) such as restaurants and religious establishments, connecting 57k CBGs to 553k POIs with 5.4 billion hourly edges. We show that by integrating these networks, a relatively simple SEIR model can accurately fit the real case trajectory, despite substantial changes in population behavior over time. Our model predicts that a small minority of “superspreader” POIs account for a large majority of infections and that restricting maximum occupancy at each POI is more effective than uniformly reducing mobility. Our model also correctly predicts higher infection rates among disadvantaged racial and socioeconomic groups solely from differences in mobility: we find that disadvantaged groups have not been able to reduce mobility as sharply, and that the POIs they visit are more crowded and therefore higher-risk. By capturing who is infected at which locations, our model supports detailed analyses that can inform more effective and equitable policy responses to COVID-19.

Jure Leskovec <http://cs.stanford.edu/~jure> is Associate Professor of Computer Science at Stanford University, Chief Scientist at Pinterest, and investigator at Chan Zuckerberg Biohub. Dr. Leskovec was the co-founder of a machine learning startup Kosei, which was later acquired by Pinterest. His research focuses on machine learning and data mining large social, information, and biological networks. Computation over massive data is at the heart of his research and has applications in computer science, social sciences, marketing, and biomedicine. This research has won several awards including a Lagrange Prize, Microsoft Research Faculty Fellowship, the Alfred P. Sloan Fellowship, and numerous best paper and test of time awards. It has also been featured in popular press outlets such as the New York Times and the Wall Street Journal. Leskovec received his bachelor’s degree in computer science from University of Ljubljana, Slovenia, PhD in machine learning from Carnegie Mellon University and postdoctoral training at Cornell University.

Evelyne Viegas

Microsoft Research

Challenges in Machine Learning – Designing high impact competitions for the benefit of society

Competitions have been used in Machine Learning as an efficient and cost-effective way to bring mature solutions that were confined to research to industries. Competitions can be used as a means of directing research, advancing the state-of-the-art or venturing in completely new domains. Over the years competition platforms have put more effort into the theoretical foundations of challenge design, the optimization of challenge protocols, and data collection. However, little thoughts have been put on how to involve the worldwide community of challenge participants and organizers in solving global challenges. In this talk, I will go over progress made in designing high impactful competitions looking at new paradigms of challenge organizations to tackle complex problems (e.g., tasks involving multiple modalities, levels of processing), large scale data, and at encouraging collaborative teams while fostering diversity in the community of participants to reduce selection bias in data collection. Finally, I’ll go over new research programs that focus on understanding the value and cost of developing large scale models that can be applied to AI innovations.

Evelyne Viegas is Senior Director of Global Research Engagement at Microsoft Research. She drives the research engagement strategy, designing collaborative programs which are open and cooperative with the external research community. She leads initiatives in the areas of Artificial Intelligence, Computing Systems and Experiences, working in partnership with the academic community, engineering and business groups, industry partners and government agencies worldwide. Prior to her present role, Evelyne worked as a Technical Lead at Microsoft delivering Natural Language Processing components to Office and Windows. Before Microsoft, and after completing her Ph.D. in France, she worked as a Principal Investigator at the Computing Research Laboratory in New Mexico on an ontology-based Machine Translation project. Evelyne serves on international editorial, program and award committees.

Denny Vrandečić

Wikimedia Foundation

Towards knowledge equity: A world where everyone can share in the sum of all knowledge

Twenty years of Wikipedia. The encyclopedia that anyone can edit has become an indispensable knowledge resource on the Web, being the foundation for many other services and technologies. But its success is very unevenly distributed, and in many languages we don’t yet provide a comprehensive and current encyclopedia. Abstract Wikipedia is a project to considerably improve the situation by providing a baseline of knowledge in many languages. It will be based on a new Wikimedia project, Wikifunctions, that will launch later this year and provide a collaboratively edited library of functions, and thus democratizing access to functions to a much wider audience. In this talk we will present the plan for Wikifunctions and Abstract Wikipedia, and how it will contribute towards our vision of a world in which everyone can share in the sum of all knowledge.

Marko Grobelnik

Jožef Stefan Institute

Cross-lingual Global Media Monitoring

Stan Matwin

Dalhousie University

Artificial Intelligence for People Emotion Detection During COVID-19 Social Isolation