Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Duarte, Rafael Mendonça, Ponciano, Jean Roberto, Valem, Lucas Pascotti
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911711160696832
author Duarte, Rafael Mendonça
Ponciano, Jean Roberto
Valem, Lucas Pascotti
author_facet Duarte, Rafael Mendonça
Ponciano, Jean Roberto
Valem, Lucas Pascotti
contents The exponential growth of data has intensified the gap between the availability of unlabeled data and the high cost of manual annotation. Graph Neural Networks (GNNs) have emerged as a promising solution, as they exploit relational structures and learn from both labeled and unlabeled data, performing semi-supervised learning. A crucial component of many of these models is degree-based normalization, which influences message propagation but typically assumes uniform importance among neighboring nodes. In image classification, graphs are usually constructed from feature similarity, where treating all neighbors equally may overlook important variations in relevance. Motivated by this gap, we propose GRaNDe (Gaussian Rank-based Neighborhood Degree). This novel degree measure integrates neighborhood ranking with Gaussian distance weighting to better capture node importance. Experiments on five public image classification datasets show consistent accuracy improvements and competitive or superior results compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24367
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification
Duarte, Rafael Mendonça
Ponciano, Jean Roberto
Valem, Lucas Pascotti
Computer Vision and Pattern Recognition
Machine Learning
The exponential growth of data has intensified the gap between the availability of unlabeled data and the high cost of manual annotation. Graph Neural Networks (GNNs) have emerged as a promising solution, as they exploit relational structures and learn from both labeled and unlabeled data, performing semi-supervised learning. A crucial component of many of these models is degree-based normalization, which influences message propagation but typically assumes uniform importance among neighboring nodes. In image classification, graphs are usually constructed from feature similarity, where treating all neighbors equally may overlook important variations in relevance. Motivated by this gap, we propose GRaNDe (Gaussian Rank-based Neighborhood Degree). This novel degree measure integrates neighborhood ranking with Gaussian distance weighting to better capture node importance. Experiments on five public image classification datasets show consistent accuracy improvements and competitive or superior results compared to state-of-the-art methods.
title Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.24367