Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation
Journal of the Brazilian Computer Society · 29.06.2026 · 32 (1) · 1731-1754
DOI: 10.5753/jbcs.2026.5880 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Brazilian Computer Society, online erschienen am 29.06.2026. Verfasst von Marina Chagas Bulach Gapski und 5 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy.
Zitieren
APA
Gapski, M. C. B., Kawai, V. A. S., Leticio, G. R., Valem, L. P., Pedronette, D. C. G., & Allili, M. S. (2026). Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation. Journal of the Brazilian Computer Society, 32(1), 1731-1754. https://doi.org/10.5753/jbcs.2026.5880
Vancouver
Gapski MCB, Kawai VAS, Leticio GR, Valem LP, Pedronette DCG, Allili MS. Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation. Journal of the Brazilian Computer Society. 2026;32(1):1731-1754. doi:10.5753/jbcs.2026.5880
BibTeX
@article{Gapski2026,
author = {Gapski, Marina Chagas Bulach and Kawai, Vinicius Atsushi Sato and Leticio, Gustavo Rosseto and Valem, Lucas Pascotti and Pedronette, Daniel Carlos Guimarães and Allili, Mohand Said},
title = {Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation},
journal = {Journal of the Brazilian Computer Society},
year = {2026},
volume = {32},
number = {1},
pages = {1731--1754},
doi = {10.5753/jbcs.2026.5880}
}
EUVIMED