Communication Dans Un Congrès Année : 2024

Continuous Product Graph Neural Networks

Résumé

Processing multidomain data defined on multiple graphs holds significant potential in various practical applications in computer science. However, current methods are mostly limited to discrete graph filtering operations. Tensorial partial differential equations on graphs (TPDEGs) provide a principled framework for modeling structured data across multiple interacting graphs, addressing the limitations of the existing discrete methodologies. In this paper, we introduce Continuous Product Graph Neural Networks (CITRUS) that emerge as a natural solution to the TPDEG. CITRUS leverages the separability of continuous heat kernels from Cartesian graph products to efficiently implement graph spectral decomposition. We conduct thorough theoretical analyses of the stability and over-smoothing properties of CITRUS in response to domain-specific graph perturbations and graph spectra effects on the performance. We evaluate CITRUS on well-known traffic and weather spatiotemporal forecasting datasets, demonstrating superior performance over existing approaches. The implementation codes are available at https://github.com/ArefEinizade2/CITRUS.
Fichier principal
Vignette du fichier
CITRUS_NeurIPS_2024.pdf (755.46 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04896043 , version 1 (19-01-2025)

Licence

Identifiants

Citer

Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo. Continuous Product Graph Neural Networks. NeurIPS 2024 - 38th Conference on Neural Information Processing Systems, Dec 2024, Vancouver (BC), Canada. ⟨hal-04896043⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More