LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Du, Lin, Bai, Lu, Li, Jincheng, Cui, Lixin, Du, Hangyuan, Zhang, Lichi, Chen, Yuting, Li, Zhao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918244449779712
author Du, Lin
Bai, Lu
Li, Jincheng
Cui, Lixin
Du, Hangyuan
Zhang, Lichi
Chen, Yuting
Li, Zhao
author_facet Du, Lin
Bai, Lu
Li, Jincheng
Cui, Lixin
Du, Hangyuan
Zhang, Lichi
Chen, Yuting
Li, Zhao
contents Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neighbor nodes, where the expressivity is limited by the 1-dimensional Weisfeiler-Lehman (1-WL) test. Although a number of k-WL-based GNNs have been proposed to overcome this limitation, their computational cost increases rapidly with k, significantly restricting the practical applicability. Moreover, since the k-WL models mainly operate on node tuples, these k-WL-based GNNs cannot retain fine-grained node- or edge-level semantics required by attribution methods (e.g., Integrated Gradients), leading to the less interpretable problem. To overcome the above shortcomings, in this paper, we propose a novel Line Graph Aggregation Network (LGAN), that constructs a line graph from the induced subgraph centered at each node to perform the higher-order aggregation. We theoretically prove that the LGAN not only possesses the greater expressive power than the 2-WL under injective aggregation assumptions, but also has lower time complexity. Empirical evaluations on benchmarks demonstrate that the LGAN outperforms state-of-the-art k-WL-based GNNs, while offering better interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10735
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation
Du, Lin
Bai, Lu
Li, Jincheng
Cui, Lixin
Du, Hangyuan
Zhang, Lichi
Chen, Yuting
Li, Zhao
Machine Learning
Artificial Intelligence
Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neighbor nodes, where the expressivity is limited by the 1-dimensional Weisfeiler-Lehman (1-WL) test. Although a number of k-WL-based GNNs have been proposed to overcome this limitation, their computational cost increases rapidly with k, significantly restricting the practical applicability. Moreover, since the k-WL models mainly operate on node tuples, these k-WL-based GNNs cannot retain fine-grained node- or edge-level semantics required by attribution methods (e.g., Integrated Gradients), leading to the less interpretable problem. To overcome the above shortcomings, in this paper, we propose a novel Line Graph Aggregation Network (LGAN), that constructs a line graph from the induced subgraph centered at each node to perform the higher-order aggregation. We theoretically prove that the LGAN not only possesses the greater expressive power than the 2-WL under injective aggregation assumptions, but also has lower time complexity. Empirical evaluations on benchmarks demonstrate that the LGAN outperforms state-of-the-art k-WL-based GNNs, while offering better interpretability.
title LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.10735