NodeNAS: Node-Specific Graph Neural Architecture Search for Out-of-Distribution Generalization

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Qiyi, Shao, Yinning, Ma, Yunlong, Liu, Min
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning Social and Information Networks
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866916644995989504
author	Wang, Qiyi Shao, Yinning Ma, Yunlong Liu, Min
author_facet	Wang, Qiyi Shao, Yinning Ma, Yunlong Liu, Min
contents	Graph neural architecture search (GraphNAS) has demonstrated advantages in mitigating performance degradation of graph neural networks (GNNs) due to distribution shifts. Recent approaches introduce weight sharing across tailored architectures, generating unique GNN architectures for each graph end-to-end. However, existing GraphNAS methods do not account for distribution patterns across different graphs and heavily rely on extensive training data. With sparse or single training graphs, these methods struggle to discover optimal mappings between graphs and architectures, failing to generalize to out-of-distribution (OOD) data. In this paper, we propose node-specific graph neural architecture search(NodeNAS), which aims to tailor distinct aggregation methods for different nodes through disentangling node topology and graph distribution with limited datasets. We further propose adaptive aggregation attention based Multi-dim NodeNAS method(MNNAS), which learns an node-specific architecture customizer with good generalizability. Specifically, we extend the vertical depth of the search space, supporting simultaneous node-specific architecture customization across multiple dimensions. Moreover, we model the power-law distribution of node degrees under varying assortativity, encoding structure invariant information to guide architecture customization across each dimension. Extensive experiments across supervised and unsupervised tasks demonstrate that MNNAS surpasses state-of-the-art algorithms and achieves excellent OOD generalization.
format	Preprint
id	arxiv_https___arxiv_org_abs_2503_02448
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	NodeNAS: Node-Specific Graph Neural Architecture Search for Out-of-Distribution Generalization Wang, Qiyi Shao, Yinning Ma, Yunlong Liu, Min Machine Learning Social and Information Networks Graph neural architecture search (GraphNAS) has demonstrated advantages in mitigating performance degradation of graph neural networks (GNNs) due to distribution shifts. Recent approaches introduce weight sharing across tailored architectures, generating unique GNN architectures for each graph end-to-end. However, existing GraphNAS methods do not account for distribution patterns across different graphs and heavily rely on extensive training data. With sparse or single training graphs, these methods struggle to discover optimal mappings between graphs and architectures, failing to generalize to out-of-distribution (OOD) data. In this paper, we propose node-specific graph neural architecture search(NodeNAS), which aims to tailor distinct aggregation methods for different nodes through disentangling node topology and graph distribution with limited datasets. We further propose adaptive aggregation attention based Multi-dim NodeNAS method(MNNAS), which learns an node-specific architecture customizer with good generalizability. Specifically, we extend the vertical depth of the search space, supporting simultaneous node-specific architecture customization across multiple dimensions. Moreover, we model the power-law distribution of node degrees under varying assortativity, encoding structure invariant information to guide architecture customization across each dimension. Extensive experiments across supervised and unsupervised tasks demonstrate that MNNAS surpasses state-of-the-art algorithms and achieves excellent OOD generalization.
title	NodeNAS: Node-Specific Graph Neural Architecture Search for Out-of-Distribution Generalization
topic	Machine Learning Social and Information Networks
url	https://arxiv.org/abs/2503.02448