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

• Rafael Mendonça Duarte Universidade de São Paulo (USP)
• Jean Roberto Ponciano Universidade de São Paulo (USP)
• Lucas Pascotti Valem Universidade de São Paulo (USP) https://orcid.org/0000-0002-3833-9072

DOI: https://doi.org/10.5753/sbbd.2026.249260

Resumo

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 accuracy improvements and competitive or favorable results compared to state-of-the-art methods. The code and supplementary materials are publicly available at grande.lucasvalem.com.

Palavras-chave: Graph Neural Networks, Image Classification, Machine Learning, Graph

Referências

Amini, M.-R., Feofanov, V., Pauletto, L., Hadjadj, L., Émilie Devijver, and Maximov, Y. (2025). Self-training: A survey. Neurocomputing, 616:128904.

Amorim, W. P., Falcão, A. X., and d. Carvalho, M. H. (2014). Semi-supervised pattern classification using optimum-path forest. In 27th SIBGRAPI Conference on Graphics, Patterns and Images, pages 111–118.

Angonese, S. F. and Galante, R. (2026). Evaluating heterogeneous node embedding compositions using diversity metrics. Journal of Information and Data Management, 17(1):17–25.

Brito, G. M. and Valem, L. P. (2025). Density-guided rank correlation graphs for graph convolutional networks in image classification. In 2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1–6.

Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., and Feng, J. (2017). Dual path networks. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 4470–4478. Curran Associates Inc.

Chen, Y., Tang, X., Qi, X., Li, C.-G., and Xiao, R. (2022). Learning graph normalization for graph neural networks. Neurocomputing, 493:613–625.

Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations.

Figuerêdo, J., Maia, A., and Calumby, R. (2023). A novel graph-based diversity-aware rank fusion method applied to image metasearch. In Anais do XXXVIII Simpósio Brasileiro de Bancos de Dados, pages 324–329, Porto Alegre, RS, Brasil. SBC.

Franceschi, L., Niepert, M., Pontil, M., and He, X. (2019). Learning discrete structures for graph neural networks. In Chaudhuri, K. and Salakhutdinov, R., editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 1972–1982. PMLR.

He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770–778.

Hu, J., Shen, L., and Sun, G. (2018). Squeeze-and-excitation networks. In 2018 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR).

Jiang, W. and Bai, Y. (2024). Sgcl: Semi-supervised graph contrastive learning with confidence propagation algorithm for node classification. Knowledge-Based Systems, 301:112271.

Khemani, B., Patil, S., Kotecha, K., and Tanwar, S. (2024). A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11(1):18.

Khosla, A., Jayadevaprakash, N., Yao, B., and Fei-Fei, L. (2011). Novel dataset for fine-grained image categorization. In First Workshop on Fine-Grained Visual Categorization, IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO.

Khoushehgir, F., Noshad, Z., Noshad, M., and Sulaimany, S. (2024). Npi-wgnn: A weighted graph neural network leveraging centrality measures and high-order common neighbor similarity for accurate ncrna–protein interaction prediction. Analytics, 3(4):476–492.

Klicpera, J., Bojchevski, A., and Günnemann, S. (2019). Combining neural networks with personalized pagerank for classification on graphs. In International Conference on Learning Representations.

Li, J., Xiong, C., and Hoi, S. C. (2021). Comatch: Semi-supervised learning with contrastive graph regularization. In International Conference on Computer Vision (ICCV), pages 9475–9484.

Liang, B., Chen, S., Gui, L., WANG, H., Yu, Y., Xu, R., and Wong, K.-F. (2025). Centrality-guided pre-training for graph. In Yue, Y., Garg, A., Peng, N., Sha, F., and Yu, R., editors, International Conference on Learning Representations, volume 2025, pages 64863–64888.

Liu, G.-H. and Yang, J.-Y. (2013). Content-based image retrieval using color difference histogram. Pattern Recognition, 46(1):188 – 198.

Nass, C., Díaz, A. O., and Baldo, F. (2021). Ssl-vfc4.5: An approach to adapt very fast c4.5 classification algorithm to deal with semi-supervised learning. In Anais do XXXVI Simpósio Brasileiro de Bancos de Dados, pages 13–24, Porto Alegre, RS, Brasil. SBC.

Nilsback, M.-E. and Zisserman, A. (2006). A visual vocabulary for flower classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, volume 2, pages 1447–1454.

Parkhi, O. M., Vedaldi, A., Zisserman, A., and Jawahar, C. V. (2012). Cats and dogs. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Presotto, J. G. C., Valem, L. P., de Sá, N. G., Pedronette, D. C. G., and Papa, J. P. (2021). Weakly supervised learning through rank-based contextual measures. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 5752–5759.

Valem, L. P., Guimarães Pedronette, D. C., and Latecki, L. J. (2023). Graph convolutional networks based on manifold learning for semi-supervised image classification. Computer Vision and Image Understanding, 227:103618.

Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (2018). Graph attention networks. In International Conference on Learning Representations.

Wah, C., Branson, S., Welinder, P., Perona, P., and Belongie, S. (2011). The Caltech-UCSD Birds-200-2011 Dataset. Technical Report CNS-TR-2011-001, California Institute of Technology.

Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K. (2019). Simplifying graph convolutional networks. In Chaudhuri, K. and Salakhutdinov, R., editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 6861–6871. PMLR.

Yang, J., Li, H., Du, B., and Ye, M. (2025). Cheb-gr: Rethinking k-nearest neighbor search in re-ranking for person re-identification. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 19261–19270.

Yu, J., Wu, Z., Lu, J., Wang, T., and Wang, H. (2025). A centrality-based graph learning framework. In Kwok, J., editor, Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25, pages 3588–3596. International Joint Conferences on Artificial Intelligence Organization. Main Track.