Communication Dans Un Congrès Année : 2024

Grammatical Path Network: You want cycles, follow this path

Résumé

In this work, we address the challenge of learning from structured data by proposing the Grammatical Path Network (GPN), a novel Graph Neural Network (GNN) designed to efficiently capture cycles in graph structures. Building on recent advancements in GNN expressiveness and substructure counting, GPN combines methodologies from Graph Substructure Networks (GSN) and a framework that translates Context Free Grammars (CFG) into GNNs. The key innovation lies in using CFG to count cycles of length l+1 by precomputing paths of length l at the edge level. Our experiments demonstrate that GPN achieves comparable performance to GSN on datasets requiring cycle information, without the need for explicit cycle precomputation. This approach offers a promising direction for developing efficient and expressive GNNs for structured data analysis.

Fichier principal
Vignette du fichier
100_Grammatical_Path_Network_Y.pdf (842.65 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05402699 , version 1 (07-12-2025)

Licence

Identifiants

  • HAL Id : hal-05402699 , version 1

Citer

Jason Piquenot, Louisa Bouzidi, Maxime Bérar, Pierre Héroux, Jean-Yves Ramel, et al.. Grammatical Path Network: You want cycles, follow this path. Learning on Graphs Conference, Nov 2024, Virtual conference, France. ⟨hal-05402699⟩
779 Consultations
111 Téléchargements

Partager

  • More