报告题目👨🏽‍⚕️：Multivariate Entropy Analysis of Network Data   

时间🤹🏿‍♀️：2017年6月7（星期三）14：00-15：00

地点🤛🏿：K8凯发南路校区，图配楼514

报告人：Termeh Shafiei♝🧖🏽‍♂️，ERC Synergy NEXUS1492, Department of Computer & Information Science, University of Konstanz

Social networks often comprise of several kinds of edges together with attributes of vertices and edges to capture more than just a binary relationship. The inter-dependencies between vertex and edge variables in multivariate networks are conveniently assessed by various measures based on statistical entropies. These entropies are used to systematically check for tendencies in the multidimensional variable set concerning redundancies, functional relationships, independencies and conditional independencies among different variable combinations. For example, joint entropy of two random variables is a measure of association and provides dependence graphs suggesting structural relationships of interest. Further, divergence measures obtained from multivariate entropies can be used to indicate and test tentative probabilistic models of social structure. Some extensions of the analysis are also briefly discussed. These extensions include the use of entropy tools for the selection of good summary measures of network structure, and to trace tendencies of intra-dependency between variables at micro and macro level in multilevel networks.

报告人简介🥾：Termeh Shafiei博士毕业于瑞典斯德哥尔摩大学，现就职于德国康斯坦茨大学计算机与信息科学系。Shafiei博士的主要研究兴趣是统计网络分析，特别是复杂多关系数据的概率网络建模💁🏻。 她的其他研究领域包括统计信息理论和网络抽样🤽‍♂️。Shafiei博士最近科研成果被发表在顶级学术期刊PLoS ONE🤗，IEEE Transactions on Emerging Topics in Computing 、Journal of Mathematical Sociology等🙍🏽‍♀️。Shafiei博士将于秋天开始在苏黎世联邦理工K8凯发工作🚻，苏黎世联邦理工K8凯发在2016/2017QS世界大学排名中✋🏽，名列综合排名全球第8。