Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kei, Yik Lun, Padilla, Oscar Hernan Madrid, Killick, Rebecca, Wilson, James, Chen, Xi, Lund, Robert
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2511.04859
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913092642799616
author Kei, Yik Lun
Padilla, Oscar Hernan Madrid
Killick, Rebecca
Wilson, James
Chen, Xi
Lund, Robert
author_facet Kei, Yik Lun
Padilla, Oscar Hernan Madrid
Killick, Rebecca
Wilson, James
Chen, Xi
Lund, Robert
contents This manuscript studies nodal clustering in graphs having multivariate attributes at each node. The framework includes node-specific priors for low-dimensional representations, coupled with a neural decoder that bridges observed attributes with latent variables. Structural and attribute information are incorporated through a graph-fused LASSO regularization on the prior means, promoting nodal clustering. The optimization problem is solved via alternating direction method of multipliers, with Langevin dynamics for posterior inference. Simulation studies on grid graphs, and applications to real data with complex settings, demonstrate the effectiveness of the proposed clustering method.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04859
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Decoder-only Clustering in Attributed Graphs
Kei, Yik Lun
Padilla, Oscar Hernan Madrid
Killick, Rebecca
Wilson, James
Chen, Xi
Lund, Robert
Methodology
Computation
This manuscript studies nodal clustering in graphs having multivariate attributes at each node. The framework includes node-specific priors for low-dimensional representations, coupled with a neural decoder that bridges observed attributes with latent variables. Structural and attribute information are incorporated through a graph-fused LASSO regularization on the prior means, promoting nodal clustering. The optimization problem is solved via alternating direction method of multipliers, with Langevin dynamics for posterior inference. Simulation studies on grid graphs, and applications to real data with complex settings, demonstrate the effectiveness of the proposed clustering method.
title Decoder-only Clustering in Attributed Graphs
topic Methodology
Computation
url https://arxiv.org/abs/2511.04859