一、活动主题
学术报告:The Applications of Graph Neural Networks to Healthy Age Prediction
二、活动时间
2023年10月15日(周日)上午10:00
三、活动地点
临潼校区图书馆一层报告厅
四、主讲嘉宾
黄德双,同济大学、宁波东方理工大学(暂名)教授,博士生导师, 中国科学技术大学兼职教授与博士生导师,俄罗斯工程院Foreign Member, IEEE Fellow,国际模式识别学会(IAPR) Fellow,亚太人工智能学会(AAIA) Fellow。
五、主讲内容
Graph Neural Networks (GNNs) have achieved advanced performance in many fields such as traffic prediction, recommendation systems, and computer vision. Recently there are majorities of methods on GNN focusing on graph convolution, and less work about pooling. To address the problems of information loss and low feature representation capability during graph pooling operations. In this report, we explore higher efficient graph-level representation learning methods and their application to bioinformatics. Firstly, to address the problem of information loss in the pooling operation, we propose a hierarchical graph-level representation learning method with self-adaptive cluster aggregation. Secondly, to address the fact that all existing graph pooling models based on mutual information maximization need to construct negative samples and usually only consider local neighborhood information, we propose a mutual information graph pooling method based on simple Siamese network. Finally, we present an application of our proposed graph-level representation learning method to healthy aging prediction by using scRNA-seq data.
六、参加人员
电信学院教师、研究生。
人事处(教师发展中心) 电子信息学院
2023年10月12日
黄德双,同济大学、宁波东方理工大学(暂名)教授,博士生导师, 中国科学技术大学兼职教授与博士生导师,俄罗斯工程院Foreign Member, IEEE Fellow,国际模式识别学会(IAPR) Fellow,亚太人工智能学会(AAIA) Fellow,2000年度中国科学院“百人计划”入选者。国家新一代人工智能重大项目首席科学家(主持人),国家科技创新2030-脑科学与类脑研究重大项目管理专家,国家自然科学基金委第十四届专家评审组成员,国家杰青、优青、重点项目函评与会评专家;国家科技部重点研发计划、国家奖会评与函评专家。中国生物信息学学会(筹)生物医学数据挖掘与计算专委会主任。获教育部自然科学一等奖一项(排名第一),安徽省自然科学一等奖一项(排名第一),获中国人工智能学会吴文俊科技进步一等奖一项(排名第一),2014-2022年度爱思唯尔(Elsevier)Scopus高被引学者(计算机科学卷)。Google Scholar引用23340余次,H因子80。