A Decoupled Embedding-Based Framework for Efficient Node Classification on Social Networks
DOI:
https://doi.org/10.5753/jisa.2026.7105Keywords:
Embedding, Graph Representation, Social Network, Machine LearningAbstract
Graph-based learning has become a cornerstone for analyzing complex relationships in domains such as social networks. However, most existing solutions rely on Graph Neural Networks (GNNs), which often require high computational resources, careful parameter tuning, and extensive training time. In this paper, we propose a decoupled learning framework for node classification that replaces end-to-end deep graph architectures with latent structural embeddings and conventional machine-learning models. Our method generates low-dimensional node embeddings and then applies classifiers such as logistic regression, KNN, and random forests to predict node categories. By structurally decoupling the embedding and classification stages, our approach achieves competitive performance while drastically reducing memory complexity and training time. Experimental results on multiple social network datasets demonstrate that our method offers a scalable, interpretable alternative to deep GNN models.
Downloads
References
Brochier, R., Guille, A., and Velcin, J. (2019). Global vectors for node representations. In The World Wide Web Conference, pages 2587-2593. DOI: 10.1145/3308558.3313595.
Cai, H., Zheng, V. W., and Chang, K. C.-C. (2018). A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE transactions on knowledge and data engineering, 30(9):1616-1637. DOI: 10.1109/tkde.2018.2807452.
Chen, Z., Tan, H., Wang, T., Shen, T., Lu, T., Peng, Q., Cheng, C., and Qi, Y. (2023). Graph propagation transformer for graph representation learning. arXiv preprint arXiv:2305.11424. DOI: 10.24963/ijcai.2023/396.
Costa, W. L., Silveira, M. M., de Araujo, T., and Gomes, R. L. (2020). Improving ddos detection in iot networks through analysis of network traffic characteristics. In 2020 IEEE Latin-American Conference on Communications (LATINCOM), pages 1-6. IEEE. DOI: 10.1109/latincom50620.2020.9282265.
Dalvi, A. and Honavar, V. (2025). Hyperdimensional representation learning for node classification and link prediction. In Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, pages 88-97. DOI: 10.1145/3701551.3703492.
Epasto, A. and Perozzi, B. (2019). Is a single embedding enough? learning node representations that capture multiple social contexts. In The world wide web conference, pages 394-404. DOI: 10.1145/3308558.3313660.
Fortunato, S. (2010). Community detection in graphs. Physics reports, 486(3-5):75-174. DOI: 10.1016/j.physrep.2009.11.002.
Goyal, P., Kamra, N., He, X., and Liu, Y. (2018). Dyngem: Deep embedding method for dynamic graphs. arXiv preprint arXiv:1805.11273. DOI: 10.48550/arxiv.1805.11273.
Heidari, F. and Papagelis, M. (2020). Evolving network representation learning based on random walks. Applied network science, 5(1):18. DOI: 10.1007/s41109-020-00257-3.
Khan, I., Bokhari, M. U., Afzal, S., and Alam, S. (2025). Distance driven graph neural network for advanced node classification through feature augmentation. Discover Computing, 28(1):70. DOI: 10.1007/s10791-025-09569-3.
Khoshraftar, S. and An, A. (2024). A survey on graph representation learning methods. ACM Transactions on Intelligent Systems and Technology, 15(1):1-55. DOI: 10.1145/3633518.
Kipf, T. (2016). Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907. DOI: 10.48550/arxiv.1609.02907.
Lecca, P. and Lecca, M. (2023). Graph embedding and geometric deep learning relevance to network biology and structural chemistry. Frontiers in Artificial Intelligence, 6:1256352. DOI: 10.3389/frai.2023.1256352.
Li, S., Zaidi, N. A., Du, M., Zhou, Z., Zhang, H., and Li, G. (2024). Property graph representation learning for node classification. Knowledge and Information Systems, 66(1):237-265. DOI: 10.1007/s10115-023-01963-x.
Lin, S., Hong, J., Lang, B., and Huang, L. (2023). Dag: Dual attention graph representation learning for node classification. Mathematics, 11(17):3691. DOI: 10.3390/math11173691.
Luo, Y., Liu, Q., Shi, L., and Wu, X.-M. (2024). Structure-aware semantic node identifiers for learning on graphs. arXiv e-prints, pages arXiv-2405. Available at:[link].
Mahdavi, S., Khoshraftar, S., and An, A. (2019). Dynamic joint variational graph autoencoders. In Joint European conference on machine learning and knowledge discovery in databases, pages 385-401. Springer. DOI: 10.1007/978-3-030-43823-4_32.
Makarov, I., Kiselev, D., Nikitinsky, N., and Subelj, L. (2021). Survey on graph embeddings and their applications to machine learning problems on graphs. PeerJ Computer Science, 7:e357. DOI: 10.7717/peerj-cs.357.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., and Dean, J. (2013). Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26. DOI: 10.48550/arxiv.1310.4546.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit-learn: Machine learning in python. the Journal of machine Learning research, 12:2825-2830. DOI: 10.48550/arxiv.1201.0490.
Pimenta, I., Silva, D., Moura, E., Silveira, M., and Gomes, R. L. (2024). Impact of data anonymization in machine learning models. In Proceedings of the 13th Latin-American Symposium on Dependable and Secure Computing, pages 188-191. DOI: 10.1145/3697090.3699865.
Pimenta, I. A., Lee, M. H., Bittencourt, L. F., and Gomes, R. L. (2025). Adaptive privacy based on mutual information for machine learning in edge-cloud environments. IEEE Networking Letters. DOI: 10.1109/lnet.2025.3607555.
Rozemberczki, B., Davies, R., Sarkar, R., and Sutton, C. (2019). Gemsec: Graph embedding with self clustering. In Proceedings of the 2019 IEEE/ACM international conference on advances in social networks analysis and mining, pages 65-72. DOI: 10.48550/arxiv.1802.03997.
Silveira, M. M., Silva, D. S., Rodriguez, S. J., and Gomes, R. L. (2022). Searchable symmetric encryption for private data protection in cloud environments. In Proceedings of the 11th Latin-American Symposium on Dependable Computing, pages 95-98. DOI: 10.1145/3569902.3570171.
Wang, D., Cui, P., and Zhu, W. (2016). Structural deep network embedding. In Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1225-1234. DOI: 10.1145/2939672.2939753.
Wang, J., Peng, J., Huang, F., Liao, S., Zhan, P., and Yi, P. (2025). Information enhancement graph representation learning. Pattern Recognition Letters. DOI: 10.1016/j.patrec.2025.04.006.
Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., and Yang, S. (2017). Community preserving network embedding. In Proceedings of the AAAI conference on artificial intelligence, volume 31. DOI: 10.1609/aaai.v31i1.10488.
Wei, X., Xu, L., Cao, B., and Yu, P. S. (2017). Cross view link prediction by learning noise-resilient representation consensus. In Proceedings of the 26th international conference on World Wide Web, pages 1611-1619. DOI: 10.1145/3038912.3052575.
Xiao, W., Zhao, H., Zheng, V. W., and Song, Y. (2020). Vertex-reinforced random walk for network embedding. In Proceedings of the 2020 SIAM International Conference on Data Mining, pages 595-603. SIAM. DOI: 10.1137/1.9781611976236.67.
Zhao, M., Huang, X., Lyu, Z., Wang, Y., Cui, L., and Bai, L. (2024). Knowledge probing for graph representation learning. arXiv preprint arXiv:2408.03877. DOI: 10.48550/arxiv.2408.03877.
Zhu, H. and Koniusz, P. (2021). Refine: Random range finder for network embedding. In Proceedings of the 30th ACM international conference on information & knowledge management, pages 3682-3686. DOI: 10.48550/arXiv.2108.10703.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Internet Services and Applications
This work is licensed under a Creative Commons Attribution 4.0 International License.
