报告人：金石教授

报告题目：Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks

报告摘要：

(1) Neural message passing is a basic feature extraction unit for graph-structured data considering neighboring node features in network propagation from one layer to the next. We model such process by an interacting particle system with attractive and repulsive forces and the Allen-Cahn force arising in the modeling of phase transition. The dynamics of the system is a reaction-diffusion process which can separate particles without blowing up. This induces an Allen-Cahn message passing (ACMP) for graph neural networks where the numerical iteration for the particle system solution constitutes the message passing propagation.

(2) ACMP which has a simple implementation with a neural ODE solver can propel the network depth up to one hundred of layers with theoretically proven strictly positive lower bound of the Dirichlet energy. It thus provides a deep model of GNNs circumventing the common GNN problem of oversmoothing. GNNs with ACMP achieve state of the art performance for real-world node classification tasks on both homophilic and heterophilic datasets.

报告时间：2022年10月29日 下午15:00-18:00

报告形式：腾讯会议；会议号：189-357-740

获取会议密码请发邮件至：yangchang@hit.edu.cn

报告人简介：金石，上海交通大学自然科学研究院经理，002资讯网讲席教授。他同时担任上海国家应用数学中心联合主任与上海交通大学重庆人工智能研究院经理。他是美国数学会首批会士，美国工业与应用数学学会会士，和2018年国际数学家大会邀请报告人，并于2021年当选为欧洲人文与自然科学院(Academia Europaea)外籍院士与欧洲科学院(European Academy of Sciences)院士。他的研究方向包括科学计算，动理学理论，多尺度计算，计算流体力学, 不确定性量化，机器学习与量子计算等。