EUVIMEDEUVIMED entdecken
Crossref

Imbalanced Node Classification in Graphs using SMOTE with GNNs

Mohd Wajahath Ullah, Dr. Kaja Masthan, Dr. Kiran B M

International Scientific Journal of Engineering and Management · 22.06.2026 · 05 (06) · 1-9

DOI: 10.55041/isjem07989 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Scientific Journal of Engineering and Management, online erschienen am 22.06.2026. Verfasst von Mohd Wajahath Ullah und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Node classification is an important research topic in graph learning. Graph neural networks (GNNs) have achieved state-of-the-art performance of node classification. However, existing GNNs address the problem where node samples for different classes are balanced; while for many real-world scenarios, some classes may have much fewer instances than others. Directly training a GNN classifier in this case would under-represent samples from those minority classes and result in sub-optimal performance. Therefore, it is very important to develop GNNs for imbalanced node classification. However, the work on this is rather limited. Hence, we seek to extend previous imbalanced learning techniques for i.i.d data to the imbalanced node classification task to facilitate GNN classifiers. In particular, we choose to adopt synthetic minority oversampling algorithms, as they are found to be the most effective and stable. This task is non-trivial, as previous synthetic minority oversampling algorithms fail to provide relation information for newly synthesized samples, which is vital for learning on graphs. Moreover, node attributes are high-dimensional. Directly over-sampling in the original input domain could generates out-of-domain samples, which may impair the accuracy of the classifier. We propose a novel framework, GraphBalance, in which an embedding space is constructed to encode the similarity among the nodes. New samples are synthesize in this space to assure genuineness. In addition, an edge generator is trained simultaneously to model the relation information, and provide it for those new samples. This framework is general and can be easily extended into different variations. The proposed framework is evaluated using three different datasets, and it outperforms all baselines with a large margin.

Zitieren

APA

Ullah, M. W., Masthan, D. K., & M, D. K. B. (2026). Imbalanced Node Classification in Graphs using SMOTE with GNNs. International Scientific Journal of Engineering and Management, 05(06), 1-9. https://doi.org/10.55041/isjem07989

Vancouver

Ullah MW, Masthan DK, M DKB. Imbalanced Node Classification in Graphs using SMOTE with GNNs. International Scientific Journal of Engineering and Management. 2026;05(06):1-9. doi:10.55041/isjem07989

BibTeX
@article{Ullah2026,
  author = {Ullah, Mohd Wajahath and Masthan, Dr. Kaja and M, Dr. Kiran B},
  title = {Imbalanced Node Classification in Graphs using SMOTE with GNNs},
  journal = {International Scientific Journal of Engineering and Management},
  year = {2026},
  volume = {05},
  number = {06},
  pages = {1--9},
  doi = {10.55041/isjem07989}
}
Kostenlos starten →