Node-level Graph Neural Architecture Search Framework

Researchers introduced N-GNAS, a Node-Level Graph Neural Architecture Search algorithm that automatically selects an appropriate network architecture for each subset of nodes when updating node features, according to an arXiv paper (arXiv:2610.09297v1). N-GNAS adds a contrastive learning loss to separate sample features from different categories, and across experiments on eight datasets for node and graph classification it outperformed current leading GNAS techniques and traditional human-designed GNNs, reaching 78.26% accuracy on the CiteSeer dataset. The work targets the over-smoothing and uniform-convolution limitations of traditional GNN approaches that apply the same convolution operations to all nodes regardless of structural and feature differences.

arXiv:2610.09297v1 Announce Type: new 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.