Guardado en:
Detalles Bibliográficos
Autores principales: Choi, Yoonhyuk, Choi, Jiho, Kim, Chanran, Lee, Yumin, Shin, Hawon, Jeon, Yeowon, Kim, Minjeong, Kang, Jiwoo
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.01207
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917182906040320
author Choi, Yoonhyuk
Choi, Jiho
Kim, Chanran
Lee, Yumin
Shin, Hawon
Jeon, Yeowon
Kim, Minjeong
Kang, Jiwoo
author_facet Choi, Yoonhyuk
Choi, Jiho
Kim, Chanran
Lee, Yumin
Shin, Hawon
Jeon, Yeowon
Kim, Minjeong
Kang, Jiwoo
contents Semi-supervised learning on real-world graphs is frequently challenged by heterophily, where the observed graph is unreliable or label-disassortative. Many existing graph neural networks either rely on a fixed adjacency structure or attempt to handle structural noise through regularization. In this work, we explicitly capture structural uncertainty by modeling a posterior distribution over signed adjacency matrices, allowing each edge to be positive, negative, or absent. We propose a sparse signed message passing network that is naturally robust to edge noise and heterophily, which can be interpreted from a Bayesian perspective. By combining (i) posterior marginalization over signed graph structures with (ii) sparse signed message aggregation, our approach offers a principled way to handle both edge noise and heterophily. Experimental results demonstrate that our method outperforms strong baseline models on heterophilic benchmarks under both synthetic and real-world structural noise.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01207
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Sparse Bayesian Message Passing under Structural Uncertainty
Choi, Yoonhyuk
Choi, Jiho
Kim, Chanran
Lee, Yumin
Shin, Hawon
Jeon, Yeowon
Kim, Minjeong
Kang, Jiwoo
Machine Learning
Semi-supervised learning on real-world graphs is frequently challenged by heterophily, where the observed graph is unreliable or label-disassortative. Many existing graph neural networks either rely on a fixed adjacency structure or attempt to handle structural noise through regularization. In this work, we explicitly capture structural uncertainty by modeling a posterior distribution over signed adjacency matrices, allowing each edge to be positive, negative, or absent. We propose a sparse signed message passing network that is naturally robust to edge noise and heterophily, which can be interpreted from a Bayesian perspective. By combining (i) posterior marginalization over signed graph structures with (ii) sparse signed message aggregation, our approach offers a principled way to handle both edge noise and heterophily. Experimental results demonstrate that our method outperforms strong baseline models on heterophilic benchmarks under both synthetic and real-world structural noise.
title Sparse Bayesian Message Passing under Structural Uncertainty
topic Machine Learning
url https://arxiv.org/abs/2601.01207