报告题目:Dynamic Data Stream Mining with Scarcity of Labels
报告时间:2024年10月29日15:00
报告地点:美高梅4688集团amE202会议室
报告人:杨圣祥
报告人单位:英国德蒙福特大学
报告人简介:1999年获东北大学博士学位。1999-2012年,分别在英国伦敦国王学院,莱斯特大学和布鲁内尔大学工作。现任英国德蒙福特大学(De Montfort University)计算机科学与信息学院教授、计算智能研究中心主任和人工智能研究院副主任。杨教授长期从事计算智能理论、方法及应用研究,在计算智能方法、演化计算求解动态优化和多目标优化问题、智能网络优化和数据流分析等方面的研究做出了突出贡献,其研究工作得到英国和欧盟研究基金会以及工业界的大力资助,先后承担了30余项科研基金项目。出版英文专著1部和英文编著2部,编辑国际会议论文集10余部,发表论文460多篇,其Google Scholar引用21500余次,H-index为75,入选2018年-2024年美国斯坦福大学发布的“全球前2%顶尖科学家”榜单。杨教授应邀担任亚洲计算智能协会副主席,担任10余种国际知名期刊副主编或编委,担任国际大会程序委员会主席和分会主席60余次,应邀做国际会议大会报告或专题报告30余次,曾任IEEE计算智能协会动态和不确定环境下的演化计算专家组主席和智能网络系统专家组创始主席。
报告摘要:Data stream mining is a natural and necessary progression from traditional data mining. However, it presents additional challenges to batch analysis: along with strict time and memory constraints, change is a major consideration. In a dynamic data stream, the underlying concepts may drift and change over time. The challenge of recognizing and reacting to change in a stream is compounded by the scarcity of labels problem. This talk presents our recent work to evaluate unsupervised learning as the basis for online classification in dynamic data streams with a scarcity of labels. A novel stream clustering algorithm based on the collective behavior of ants, called Ant Colony Stream Clustering (ACSC), is present. Furthermore, a novel framework, Clustering and One class Classification Ensemble Learning (COCEL), for classification in dynamic streams with a scarcity of labels is described. The proposed framework can identify and react to change in a stream and hugely reduces the number of required labels (typically less than 0.05% of the entire stream). Finally, some conclusions will be made.
邀请人:王峰