Guardado en:
Detalles Bibliográficos
Autores principales: Jiang, Yuanhong, Zou, Dongmian, Zhang, Xiaoqun, Wang, Yu Guang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2407.06988
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913144990859264
author Jiang, Yuanhong
Zou, Dongmian
Zhang, Xiaoqun
Wang, Yu Guang
author_facet Jiang, Yuanhong
Zou, Dongmian
Zhang, Xiaoqun
Wang, Yu Guang
contents Graph neural networks (GNNs) have become pivotal tools for processing graph-structured data, leveraging the message passing scheme as their core mechanism. However, traditional GNNs often grapple with issues such as instability, over-smoothing, and over-squashing, which can degrade performance and create a trade-off dilemma. In this paper, we introduce a discriminatively trained, multi-layer Deep Scattering Message Passing (DSMP) neural network designed to overcome these challenges. By harnessing spectral transformation, the DSMP model aggregates neighboring nodes with global information, thereby enhancing the precision and accuracy of graph signal processing. We provide theoretical proofs demonstrating the DSMP's effectiveness in mitigating these issues under specific conditions. Additionally, we support our claims with empirical evidence and thorough frequency analysis, showcasing the DSMP's superior ability to address instability, over-smoothing, and over-squashing.
format Preprint
id arxiv_https___arxiv_org_abs_2407_06988
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Limiting Over-Smoothing and Over-Squashing of Graph Message Passing by Deep Scattering Transforms
Jiang, Yuanhong
Zou, Dongmian
Zhang, Xiaoqun
Wang, Yu Guang
Spectral Theory
Graph neural networks (GNNs) have become pivotal tools for processing graph-structured data, leveraging the message passing scheme as their core mechanism. However, traditional GNNs often grapple with issues such as instability, over-smoothing, and over-squashing, which can degrade performance and create a trade-off dilemma. In this paper, we introduce a discriminatively trained, multi-layer Deep Scattering Message Passing (DSMP) neural network designed to overcome these challenges. By harnessing spectral transformation, the DSMP model aggregates neighboring nodes with global information, thereby enhancing the precision and accuracy of graph signal processing. We provide theoretical proofs demonstrating the DSMP's effectiveness in mitigating these issues under specific conditions. Additionally, we support our claims with empirical evidence and thorough frequency analysis, showcasing the DSMP's superior ability to address instability, over-smoothing, and over-squashing.
title Limiting Over-Smoothing and Over-Squashing of Graph Message Passing by Deep Scattering Transforms
topic Spectral Theory
url https://arxiv.org/abs/2407.06988