IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Junchao, Ling, Zenan, Feng, Zhanbo, Xu, Jingwen, Liao, Minxuan, Zhou, Feng, Hou, Tianqi, Liao, Zhenyu, Qiu, Robert C.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910833749000192
author Lin, Junchao
Ling, Zenan
Feng, Zhanbo
Xu, Jingwen
Liao, Minxuan
Zhou, Feng
Hou, Tianqi
Liao, Zhenyu
Qiu, Robert C.
author_facet Lin, Junchao
Ling, Zenan
Feng, Zhanbo
Xu, Jingwen
Liao, Minxuan
Zhou, Feng
Hou, Tianqi
Liao, Zhenyu
Qiu, Robert C.
contents Implicit graph neural networks (IGNNs), which exhibit strong expressive power with a single layer, have recently demonstrated remarkable performance in capturing long-range dependencies (LRD) in underlying graphs while effectively mitigating the over-smoothing problem. However, IGNNs rely on computationally expensive fixed-point iterations, which lead to significant speed and scalability limitations, hindering their application to large-scale graphs. To achieve fast fixed-point solving for IGNNs, we propose a novel graph neural solver, IGNN-Solver, which leverages the generalized Anderson Acceleration method, parameterized by a tiny GNN, and learns iterative updates as a graph-dependent temporal process. To improve effectiveness on large-scale graph tasks, we further integrate sparsification and storage compression methods, specifically tailored for the IGNN-Solver, into its design. Extensive experiments demonstrate that the IGNN-Solver significantly accelerates inference on both small- and large-scale tasks, achieving a $1.5\times$ to $8\times$ speedup without sacrificing accuracy. This advantage becomes more pronounced as the graph scale grows, facilitating its large-scale deployment in real-world applications. The code to reproduce our results is available at https://github.com/landrarwolf/IGNN-Solver.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08524
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks
Lin, Junchao
Ling, Zenan
Feng, Zhanbo
Xu, Jingwen
Liao, Minxuan
Zhou, Feng
Hou, Tianqi
Liao, Zhenyu
Qiu, Robert C.
Machine Learning
Implicit graph neural networks (IGNNs), which exhibit strong expressive power with a single layer, have recently demonstrated remarkable performance in capturing long-range dependencies (LRD) in underlying graphs while effectively mitigating the over-smoothing problem. However, IGNNs rely on computationally expensive fixed-point iterations, which lead to significant speed and scalability limitations, hindering their application to large-scale graphs. To achieve fast fixed-point solving for IGNNs, we propose a novel graph neural solver, IGNN-Solver, which leverages the generalized Anderson Acceleration method, parameterized by a tiny GNN, and learns iterative updates as a graph-dependent temporal process. To improve effectiveness on large-scale graph tasks, we further integrate sparsification and storage compression methods, specifically tailored for the IGNN-Solver, into its design. Extensive experiments demonstrate that the IGNN-Solver significantly accelerates inference on both small- and large-scale tasks, achieving a $1.5\times$ to $8\times$ speedup without sacrificing accuracy. This advantage becomes more pronounced as the graph scale grows, facilitating its large-scale deployment in real-world applications. The code to reproduce our results is available at https://github.com/landrarwolf/IGNN-Solver.
title IGNN-Solver: A Graph Neural Solver for Implicit Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2410.08524