网站地图 | 联系我们 | English | 意见反馈 | 主任信箱
 
首页 中心概况 新闻动态 科研进展 交流合作 人才培养 研究队伍 人才招聘 政策规章 数学交叉科学传播
学术报告
现在位置:首页 > 学术报告

Generalization of Graph Neural Networks and Graph Structural Learning for Robust Representation
【2023.3.15 10:00am, 腾讯会议】

【打印】【关闭】

   2023-3-7 

  Colloquia & Seminars 

  

  Speaker

吕绍高教授,南京审计大学统计与数据科学学院

  Title

Generalization of Graph Neural Networks and Graph Structural Learning for Robust Representation

  Time

3月15日10:00

  Venue

腾讯会议:102-382-001

  Abstract

  This report consists of two parts associated with graph neural networks: generalization and graph structural learning. We first study the Rademacher complexity of GNNs, as one of independent-algorithm generalization measurements. In addition, we also give upper bounds of the uniform stability of proximal SGD of $L_p$-regularized GNN, which is also used as generalization ability of some specific algorithm. Importantly, inspired by our theoretical findings, we propose a new graph structure learning to generate a clean adjacency matrix for downstream robust representation and learning. Several experiments over real graph data is implemented to show comparable performances of the proposed method on GNNs. 

  Affiliation

  现为南京审计大学统计与数据科学学院教授,博士生导师。2011年毕业于中国科大-香港城市大学联合培养项目,获得理学博士学位。主要研究方向是统计机器学习,当前研究兴趣包括联邦学习、再生核方法以及深度学习与图神经网络。迄今为止在SCI检索的国际期刊上发表论文30多篇,包括统计学期刊《Annals of Statistics》2篇、人工智能类期刊《Journal of Machine Learning Research》3篇、“NeurIPS”与《Journal of Econometrics》各1篇。曾主持过国家自然科学基金项目2项。长期担任人工智能顶级会议“NeurIPS”、“ICML”、“AAAI”以及“AIStat”程序委员或审稿人。

  

  

欢迎访问国家数学与交叉科学中心 
地址:北京海淀区中关村东路55号 邮编:100190 电话: 86-10-62613242 Fax: 86-10-62616840 邮箱: ncmis@amss.ac.cn