Local-to-global Perspectives on Graph Neural Networks

Chen Cai

Local-to-global Perspectives on Graph Neural Networks

Machine Learning 2023-06-21 v2 Machine Learning

Authors: Chen Cai

Abstract

This thesis presents a local-to-global perspective on graph neural networks (GNN), the leading architecture to process graph-structured data. After categorizing GNN into local Message Passing Neural Networks (MPNN) and global Graph transformers, we present three pieces of work: 1) study the convergence property of a type of global GNN, Invariant Graph Networks, 2) connect the local MPNN and global Graph Transformer, and 3) use local MPNN for graph coarsening, a standard subroutine used in global modeling.

Keywords

graph neural network graph signal processing graph convolutional network

Cite

@article{arxiv.2306.06547,
  title  = {Local-to-global Perspectives on Graph Neural Networks},
  author = {Chen Cai},
  journal= {arXiv preprint arXiv:2306.06547},
  year   = {2023}
}

Comments

Ph.D. thesis from UC San Diego that includes three works arXiv:2201.10129, arXiv:2301.11956, arXiv:2102.01350

Related papers

View all related →