Node-level Graph Neural Architecture Search Framework

2026-10-06

AI Summary

This study addresses the limitation of traditional graph neural networks (GNNs) that apply uniform convolution across all nodes, neglecting local structural heterogeneity and thereby inducing performance bottlenecks and over-smoothing. To overcome this, we propose N-GNAS, an algorithm integrating neural architecture search (NAS) with contrastive learning to automatically discover optimal network architectures for distinct node subsets, enabling heterogeneous feature updates. Furthermore, a contrastive loss is incorporated to enhance inter-class feature separability. Extensive experiments demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches across eight benchmark datasets, achieving a node classification accuracy of 78.26% on CiteSeer.

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.

Problem

• Graph Neural Networks
• Neural Architecture Search
• Over-smoothing
• Node-level

Innovation

• Graph Neural Architecture Search
• Node-Level
• Contrastive Learning
• Over-smoothing
• Graph Neural Networks