Learnability of Competitive Threshold Models

European Conference on Artificial Intelligence(2022)

引用 2|浏览14
暂无评分
摘要
Modeling the spread of social contagions is central to various applications in social computing. In this paper, we study 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 design 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.
更多
查看译文
关键词
Multidisciplinary Topics and Applications: Web and Social Networks,Data Mining: Mining Graphs,Data Mining: Theoretical Foundations of Data Mining,Machine Learning: Learning Theory,Multidisciplinary Topics and Applications: Social Sciences
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要