中科院数学与系统科学研究院

数学研究所

综合报告会

（Colloquium）

报告人：吴信东 教授(合肥工业大学)

题  目：Online Feature Selection with Streaming Features

时  间：2016.6.20 (星期一) , 09:00-10:00

地  点：数学院南楼N902室

Abstract :

Online feature selection with streaming features refers to applications where the knowledge of the full feature space is unknown in advance and features flow in one by one over time. This is in contrast with traditional online learning methods that only deal with sequentially added data instances, with little attention being paid to streaming features. The critical challenges for online streaming feature selection include (1) the continuous growth of feature volumes over time, (2) a large feature space, possibly of unknown or infinite size, and (3) the unavailability of the entire feature set before learning starts. This talk introduces our recent research efforts on online streaming feature selection to select strongly relevant and non-redundant features on the fly.

简介：

吴信东，合肥工业大学长江学者，美国佛蒙特大学计算机科学系教授，“多源海量动态信息处理”教育部创新团队带头人、IEEE & AAAS Fellow。于2005至2008年期间担任两届TKDE主编，是Knowledge and Information System的现任主编，IEEE ICDM 的指导委员会主席。2004年获得了ACM SIGKDD奉献奖，2006年获得了IEEE ICDM杰出奉献奖, 2012年获IEEE 计算机学会技术进步奖, 2014年获得ICDM 10年最有影响力论文奖。