arXiv：cs.LG· Lintao Yanga, Sirui Lia, Yaqing Wang, Pietro Li\`o, Xu Shen, Baisong Liu, Chengbin Peng·· 3 小时前AI 评分32
N-GNAS：节点级图神经网络架构搜索框架
Node-level Graph Neural Architecture Search Framework
AI 导读
研究者提出节点级图神经网络架构搜索算法 N-GNAS，可在更新节点特征时为每个节点子集自动选择合适网络架构，并引入对比学习损失分离不同类别样本特征。在八个节点分类与图分类数据集上，N-GNAS 优于当前主流 GNAS 方法和人工设计的 GNN，例如在 CiteSeer 数据集上达到 78.26% 准确率。
正文
Abstract:In recent years, Graph Neural Networks (GNNs) and architecture search frameworks have gained extensive application in non-Euclidean data processing, attributable to their superior capacity in managing unstructured data. Nevertheless, traditional approaches typically apply uniform convolution operations to all nodes, regardless of their varying structural and feature characteristics, which can undermine model performance and result in over-smoothing issues as the number of layers increases. To overcome this limitation, in this work, we propose a \textbf{N}ode-Level \textbf{G}raph \textbf{N}eural \textbf{A}rchitecture \textbf{S}earch (N-GNAS) algorithm. It can automatically choose an appropriate network architecture for each subset of nodes when updating node features. N-GNAS also introduces a contrastive learning loss to separate sample features from different categories and vice versa. In experiments conducted on eight datasets for node and graph classification, our methodology outperforms current leading GNAS techniques and traditional human-designed GNNs. For example, it achieves an accuracy rate of 78.26\% on the CiteSeer dataset.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.09297 [cs.LG] |
| (or arXiv:2610.09297v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09297 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sirui Li [view email]
[v1]
Wed, 7 Oct 2026 01:58:33 UTC (1,442 KB)
来源：arXiv：cs.LG · arxiv.org