Saved in:
Bibliographic Details
Main Authors: Wang, Yuelin, Yi, Kai, Liu, Xinliang, Wang, Yu Guang, Jin, Shi
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2206.05437
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909700219469824
author Wang, Yuelin
Yi, Kai
Liu, Xinliang
Wang, Yu Guang
Jin, Shi
author_facet Wang, Yuelin
Yi, Kai
Liu, Xinliang
Wang, Yu Guang
Jin, Shi
contents 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. 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. Codes are available at https://github.com/ykiiiiii/ACMP.
format Preprint
id arxiv_https___arxiv_org_abs_2206_05437
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
Wang, Yuelin
Yi, Kai
Liu, Xinliang
Wang, Yu Guang
Jin, Shi
Machine Learning
Artificial Intelligence
Analysis of PDEs
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. 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. Codes are available at https://github.com/ykiiiiii/ACMP.
title ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
topic Machine Learning
Artificial Intelligence
Analysis of PDEs
url https://arxiv.org/abs/2206.05437