Graph Neural Diffusion via Generalized Opinion Dynamics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hevapathige, Asela, Wijesinghe, Asiri, Zehmakan, Ahad N.
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915447493885952
author Hevapathige, Asela
Wijesinghe, Asiri
Zehmakan, Ahad N.
author_facet Hevapathige, Asela
Wijesinghe, Asiri
Zehmakan, Ahad N.
contents There has been a growing interest in developing diffusion-based Graph Neural Networks (GNNs), building on the connections between message passing mechanisms in GNNs and physical diffusion processes. However, existing methods suffer from three critical limitations: (1) they rely on homogeneous diffusion with static dynamics, limiting adaptability to diverse graph structures; (2) their depth is constrained by computational overhead and diminishing interpretability; and (3) theoretical understanding of their convergence behavior remains limited. To address these challenges, we propose GODNF, a Generalized Opinion Dynamics Neural Framework, which unifies multiple opinion dynamics models into a principled, trainable diffusion mechanism. Our framework captures heterogeneous diffusion patterns and temporal dynamics via node-specific behavior modeling and dynamic neighborhood influence, while ensuring efficient and interpretable message propagation even at deep layers. We provide a rigorous theoretical analysis demonstrating GODNF's ability to model diverse convergence configurations. Extensive empirical evaluations of node classification and influence estimation tasks confirm GODNF's superiority over state-of-the-art GNNs.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11249
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph Neural Diffusion via Generalized Opinion Dynamics
Hevapathige, Asela
Wijesinghe, Asiri
Zehmakan, Ahad N.
Machine Learning
Artificial Intelligence
There has been a growing interest in developing diffusion-based Graph Neural Networks (GNNs), building on the connections between message passing mechanisms in GNNs and physical diffusion processes. However, existing methods suffer from three critical limitations: (1) they rely on homogeneous diffusion with static dynamics, limiting adaptability to diverse graph structures; (2) their depth is constrained by computational overhead and diminishing interpretability; and (3) theoretical understanding of their convergence behavior remains limited. To address these challenges, we propose GODNF, a Generalized Opinion Dynamics Neural Framework, which unifies multiple opinion dynamics models into a principled, trainable diffusion mechanism. Our framework captures heterogeneous diffusion patterns and temporal dynamics via node-specific behavior modeling and dynamic neighborhood influence, while ensuring efficient and interpretable message propagation even at deep layers. We provide a rigorous theoretical analysis demonstrating GODNF's ability to model diverse convergence configurations. Extensive empirical evaluations of node classification and influence estimation tasks confirm GODNF's superiority over state-of-the-art GNNs.
title Graph Neural Diffusion via Generalized Opinion Dynamics
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.11249