报告题目:Learnability of Competitive Threshold Models

报告时间：2023年2月23日（星期四）9:00-10:00

报告方式：腾讯会议，会议号744-8325-9832

报告摘要：Modeling the spread of social contagions is central to various applications in social computing. In this talk, we will discuss the learnability of the competitive threshold model from a theoretical perspective. We demonstrate how competitive threshold models can be seamlessly simulated by artificial neural networks with finite VC dimensions, which enables analytical sample complexity and generalization bounds. Based on the proposed hypothesis space, we present efficient algorithms under the empirical risk minimization scheme. The theoretical insights are finally translated into practical and explainable modeling methods, the effectiveness of which is verified through a sanity check over a few synthetic and real datasets. The experimental results promisingly show that our method enjoys a decent performance without using excessive data points, outperforming off-the-shelf methods. （该工作发表于IJCAI2022）

报告人简介：Dr. Guangmo Tong is an Assistant Professor in the Department of Computer and Information Sciences at the University of Delaware. He received a Ph.D. in Computer Science from the University of Texas at Dallas, and a BS degree in Mathematics and Applied Mathematics from Beijing Institute of Technology. His research interests include combinatorial optimization, machine learning, and computational social systems.