报告题目：Generalization of Graph Neural Networks and Graph Structural Learning for Robust Representation
报 告 人：吕绍高 (南京审计大学 教授)
报告时间：2022-11-10(星期四) 13:30开始
报告地点：腾讯会议，会议号：559-783-740
报告摘要：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.
专家简介：吕绍高，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20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。
