Saved in:
Bibliographic Details
Main Authors: Wang, Yingxu, Yin, Nan, Xiao, Mingyan, Yi, Xinhao, Liu, Siwei, Liang, Shangsong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.10000
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911247179448320
author Wang, Yingxu
Yin, Nan
Xiao, Mingyan
Yi, Xinhao
Liu, Siwei
Liang, Shangsong
author_facet Wang, Yingxu
Yin, Nan
Xiao, Mingyan
Yi, Xinhao
Liu, Siwei
Liang, Shangsong
contents Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often overlook the over-smoothing issue caused by traditional GNN models, as well as the gradient explosion or vanishing problems in deep GNNs. (2) Most models operate on first-order information, neglecting that the real world often consists of second-order systems, which further limits the model's representation capabilities. To address these issues, we propose the \textbf{Du}al \textbf{S}econd-order \textbf{E}quivariant \textbf{G}raph \textbf{O}rdinary Differential Equation (\method{}) for equivariant representation. Specifically, \method{} apply the dual second-order equivariant graph ordinary differential equations (Graph ODEs) on graph embeddings and node coordinates, simultaneously. Theoretically, we first prove that \method{} maintains the equivariant property. Furthermore, we provide theoretical insights showing that \method{} effectively alleviates the over-smoothing problem in both feature representation and coordinate update. Additionally, we demonstrate that the proposed \method{} mitigates the exploding and vanishing gradients problem, facilitating the training of deep multi-layer GNNs. Extensive experiments on benchmark datasets validate the superiority of the proposed \method{} compared to baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10000
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DuSEGO: Dual Second-order Equivariant Graph Ordinary Differential Equation
Wang, Yingxu
Yin, Nan
Xiao, Mingyan
Yi, Xinhao
Liu, Siwei
Liang, Shangsong
Machine Learning
Artificial Intelligence
Graph Neural Networks (GNNs) with equivariant properties have achieved significant success in modeling complex dynamic systems and molecular properties. However, their expressiveness ability is limited by: (1) Existing methods often overlook the over-smoothing issue caused by traditional GNN models, as well as the gradient explosion or vanishing problems in deep GNNs. (2) Most models operate on first-order information, neglecting that the real world often consists of second-order systems, which further limits the model's representation capabilities. To address these issues, we propose the \textbf{Du}al \textbf{S}econd-order \textbf{E}quivariant \textbf{G}raph \textbf{O}rdinary Differential Equation (\method{}) for equivariant representation. Specifically, \method{} apply the dual second-order equivariant graph ordinary differential equations (Graph ODEs) on graph embeddings and node coordinates, simultaneously. Theoretically, we first prove that \method{} maintains the equivariant property. Furthermore, we provide theoretical insights showing that \method{} effectively alleviates the over-smoothing problem in both feature representation and coordinate update. Additionally, we demonstrate that the proposed \method{} mitigates the exploding and vanishing gradients problem, facilitating the training of deep multi-layer GNNs. Extensive experiments on benchmark datasets validate the superiority of the proposed \method{} compared to baselines.
title DuSEGO: Dual Second-order Equivariant Graph Ordinary Differential Equation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2411.10000