04/10
2023
Seminar
- Title题目 STATISTICAL MECHANICS OF GRAPH NEURAL NETWORKS
- Speaker报告人 施成 (University of Basel)
- Date日期 2023年4月10日 15:00
- Venue地点 南楼6620
Abstract摘要
Graph convolution networks are excellent models for relational data but their success is not well understood. I will show how ideas from statistical physics and random matrix theory allow us to precisely characterize GCN generalization on the contextual stochastic block model—a community-structured graph model with features. The resulting curves are rich: they predict double descent thus far unseen in graph learning and explain the qualitative distinction between learning on homophilic graphs (such as friendship networks) and heterophilic graphs (such as protein interaction networks). Earlier approaches based on VC-dimension or Rademacher complexity are too blunt to yield similar mechanistic insight. Our findings pleasingly translate to real “production-scale” networks and datasets and suggest simple redesigns which improve performance of state-of-the-art networks on heterophilic datasets. They further suggest intriguing connections with spectral graph theory, signal processing, and iterative methods for the Helmholtz equation. Joint work with Liming Pan, Hong Hu and Ivan Dokmanic.
个人简介：Cheng Shi received this bachelor degree from University of Electronic Science and Technology of China in 2019. He is currently a third-year Ph.D. student at the University of Basel, supervised by Ivan Dokmanic and Martin Vetterli.
邀请人 ：张潘
附件下载: