Integrated Deep Unsupervised Models Into An Advance Ensemble Framework For Detecting Anomalies In Attributed Social Networks
DOI:
https://doi.org/10.29284/0p5mm147Keywords:
Anomaly Detection, Social Network Analysis, Ensemble Learning, Deep Generative Models, Unsupervised Learning.Abstract
Anomaly detection has become a major challenge in social network analysis, due to the significant applications of improper activity (such as fraud and spam detection), where the integration of graph topology and node attributes enables more accurate identification of anomalous nodes in networks with static characteristics. Although the rise of deep learning has occurred to overcome the scalability limitations of classical methods in the face of increasing volume and dimension of data, the major reliance on supervised techniques is still hampered by the lack of labeled data and the inherent unavailability of ground truth in anomaly detection tasks in the real world. Although unexplored strategies have been developed for using allele data, their efficacy is inherently limited by the diversity of anomaly types, as no single model can universally capture all possible aberrations. To overcome this fundamental limitation, we propose a new unsupervised ensemble framework that synergistically combines the representational capability of Autoencoder (AE), Variational Autoencoder (VAE) and Generative Adversarial Network (GAN), and incorporates a new weighting mechanism to dynamically aggregate the identities from each component model during the inference phase. Extensive evaluations on the BlogCatalog and Flickr datasets conclusively demonstrate that our ensemble approach is significantly superior to the performance of each individual state-of-the-art model used alone.
References
[1] L. Zhen, N. Hafizah Kamarudin, V. Jyn Kok and F. Qamar, "Anomaly Detection Model in Network Security Situational Awareness Based on Machine Learning: Limitation, Techniques, and Future Trends," in IEEE Access, vol. 13, pp. 126084-126129, 2025, doi: https://doi.org/10.1109/ACCESS.2025.3589620.
[2] Kesavulu, D., R, K. Improved bio-inspired with machine learning computing approach for thyroid prediction. Sci Rep 15, 22524 (2025). https://doi.org/10.1038/s41598-025-03299-8
[3] Schnoering, H., & Vazirgiannis, M. (2025). Bitcoin research with a transaction graph dataset. Scientific Data, 12(1), 404. doi : https://doi.org/10.1038/s41597-025-04684-8.
[4] Khan, M. Z., Shahzadi, M., Khan, A., Ali, U., Hassan, M. A. S., & Hussain, M. (2025). Review on crack detection in civil infrastructure using structural health monitoring and machine learning techniques. Innovative Infrastructure Solutions, 10(8), 348. doi : https://doi.org/10.1007/s41062-025-02147-y.
[5] Feng, C., Fan, J., Liu, Z., Jin, G., & Chen, S. (2025). Unmanned Aerial Vehicle Anomaly Detection Based on Causality-Enhanced Graph Neural Networks. Drones, 9(6), 408. doi : https://doi.org/10.3390/drones9060408.
[6] Gad, I. (2025). TOCA-IoT: Threshold optimization and causal analysis for IoT network anomaly detection based on explainable random forest. Algorithms, 18(2), 117. doi : https://doi.org/10.3390/a18020117.
[7] Usama, M., Qadir, J., Raza, A., Arif, H., Yau, K. L. A., Elkhatib, Y., ... & Al-Fuqaha, A. (2019). Unsupervised machine learning for networking: Techniques, applications and research challenges. IEEE access, 7, 65579-65615, doi: https://doi.org/10.1109/ACCESS.2019.2916648
[8] Mascali, L., Schiera, D. S., Eiraudo, S., Barbierato, L., Giannantonio, R., Patti, E., ... & Lanzini, A. (2023). A machine learning-based Anomaly Detection Framework for building electricity consumption data. Sustainable Energy, Grids and Networks, 36, 101194, doi: https://doi.org/10.1016/j.segan.2023.101194.
[9] Shrish Bajpai, “Low Complexity and Low Memory Compression Algorithm for Hyperspectral Image Sensors,” Wireless Personal Communications, vol. 131, pp. 805-833, 2023.
[10] Xing, L., Li, S., Zhang, Q., Wu, H., Ma, H., & Zhang, X. (2024). A survey on social network’s anomalous behavior detection. Complex & Intelligent Systems, 10(4), 5917-5932, doi: https://doi.org/10.1007/s40747-024-01446-8.
[11] Khosravi, P., Mohammadi, S., Zahiri, F., Khodarahmi, M., & Zahiri, J. (2024). AI‐enhanced detection of clinically relevant structural and functional anomalies in MRI: Traversing the landscape of conventional to explainable approaches. Journal of Magnetic Resonance Imaging, 60(6), 2272-2289, doi: https://doi.org/10.1002/jmri.29247.
[12] Zamanzadeh Darban, Z., Webb, G. I., Pan, S., Aggarwal, C., & Salehi, M. (2024). Deep learning for time series anomaly detection: A survey. ACM Computing Surveys, 57(1), 1-42, doi: https://doi.org/10.1145/3691338
[13] Su, J., Jiang, C., Jin, X., Qiao, Y., Xiao, T., Ma, H., ... & Lin, J. (2024). Large language models for forecasting and anomaly detection: A systematic literature review. arXiv preprint arXiv:2402.10350, doi: https://doi.org/10.1002/jmri.29247.
[14] Taye, M. M. (2023). Understanding of machine learning with deep learning: architectures, workflow, applications and future directions. Computers, 12(5), 91, doi: https://doi.org/10.3390/computers12050091.
[15] Liu, R., Gupta, S., & Patel, P. (2023). The application of the principles of responsible AI on social media marketing for digital health. Information Systems Frontiers, 25(6), 2275-2299, doi: https://doi.org/10.1007/s10796-021-10191-z.
[16] Baradaran, M., & Bergevin, R. (2024). A critical study on the recent deep learning based semi-supervised video anomaly detection methods. Multimedia Tools and Applications, 83(9), 27761-27807, doi: https://doi.org/10.63313/JCSFT.9001.
[17] Divya Sharma, Y.K. Prajapati, and R. Tripathi, “Success Journey of Coherent PM-QPSK Technique with Its Variants: A Survey,” IETE Technical Review, vol. 37, no. 1, pp. 36-55, 2020.
[18] Shafi, M., Lashkari, A. H., Rodriguez, V., & Nevo, R. (2024). Toward generating a new cloud-based Distributed Denial of Service (DDoS) dataset and cloud intrusion traffic characterization. Information, 15(4), 195, doi: https://doi.org/10.3390/info15040195.
[19] Berahmand, K., Daneshfar, F., Salehi, E. S., Li, Y., & Xu, Y. (2024). Autoencoders and their applications in machine learning: a survey. Artificial intelligence review, 57(2), 28, doi: https://doi.org/10.1007/s10462-023-10662-6.
[20] Ijiga, O. M., Idoko, I. P., Ebiega, G. I., Olajide, F. I., Olatunde, T. I., & Ukaegbu, C. (2024). Harnessing adversarial machine learning for advanced threat detection: AI-driven strategies in cybersecurity risk assessment and fraud prevention. J. Sci. Technol, 11, 001-024, doi: https://doi.org/10.53022/oarjst.2024.11.1.0060.
[21] Xing, L., Li, S., Zhang, Q., Wu, H., Ma, H., & Zhang, X. (2024). A survey on social network’s anomalous behavior detection. Complex & Intelligent Systems, 10(4), 5917-5932, doi: https://doi.org/10.1007/s40747-024-01446-8.
[22] Liu, R., Shi, J., Chen, X., & Lu, C. (2024). Network anomaly detection and security defense technology based on machine learning: A review. Computers and Electrical Engineering, 119, 109581, doi: https://doi.org/10.1016/j.compeleceng.2024.109581.
[23] Qiao, H., Tong, H., An, B., King, I., Aggarwal, C., & Pang, G. (2025). Deep graph anomaly detection: A survey and new perspectives. IEEE Transactions on Knowledge and Data Engineering, pp 5106 – 5126, doi: https://doi.org/10.1109/TKDE.2025.3581578.
[24] Rane, N., Choudhary, S. P., & Rane, J. (2024). Ensemble deep learning and machine learning: applications, opportunities, challenges, and future directions. Studies in Medical and Health Sciences, 1(2), 18-41, doi: https://doi.org/10.48185/smhs.v1i2.1225.
[25] Iqbal, A., Amin, R., Alsubaei, F. S., & Alzahrani, A. (2024). Anomaly detection in multivariate time series data using deep ensemble models. Plos one, 19(6), e0303890, doi: 10.1371/journal.pone.0303890.
[26] Lapid, S., Kagan, D., & Fire, M. (2023). Co-membership-based generic anomalous communities’ detection. Neural Processing Letters, 55(5), 5619-5651, doi: https://doi.org/10.1007/s11063-022-11103-1.
[27] Veesam, S. B., Satish, A. R., Tupakula, S., Chinnam, Y., Prakash, K., Bansal, S., & Faruque, M. R. I. (2025). Design of an integrated model with temporal graph attention and transformer-augmented RNNs for enhanced anomaly detection. Scientific Reports, 15(1), 2692, doi: https://doi.org/10.1038/s41598-025-85822-5.
[28] Huang, H., Wang, P., Pei, J., Wang, J., Alexanian, S., & Niyato, D. (2025). Deep learning advancements in anomaly detection: A comprehensive survey. IEEE Internet of Things Journal, pp 1-1, doi: https://doi.org/10.1109/JIOT.2025.3585884.
[29] Liu, J., Liu, Y., Lin, J., Li, J., Cao, L., Sun, P., ... & Leung, V. C. (2025). Networking systems for video anomaly detection: A tutorial and survey. ACM Computing Surveys, 57(10), 1-37, doi: https://doi.org/10.1145/3729222.
[30] Bhatti, U. A., Tang, H., Wu, G., Marjan, S., & Hussain, A. (2023). Deep learning with graph convolutional networks: An overview and latest applications in computational intelligence. International Journal of Intelligent Systems, 2023(1), 8342104, doi: https://doi.org/10.1155/2023/8342104.
[31] Fan, H., Wang, R., Huang, X., Zhang, F., Li, Z., & Su, S. (2024). Deep joint adversarial learning for anomaly detection on attribute networks. Information Sciences, 654, 119840, doi: https://doi.org/10.1016/j.ins.2023.119840.
[32] Khan, W., Mohd, A., Suaib, M., Ishrat, M., Shaikh, A. A., & Faisal, S. M. (2025). Residual-enhanced graph convolutional networks with hypersphere mapping for anomaly detection in attributed networks. Data Science and Management, 8(2), 137-146, doi: https://doi.org/10.1016/j.dsm.2024.09.002.
[33] Dash, A., Ye, J., & Wang, G. (2023). A review of generative adversarial networks (GANs) and its applications in a wide variety of disciplines: from medical to remote sensing. IEEE Access, 12, 18330-18357, doi: https://doi.org/10.1109/ACCESS.2023.3346273.
[34] Rane, N., Choudhary, S. P., & Rane, J. (2024). Ensemble deep learning and machine learning: applications, opportunities, challenges, and future directions. Studies in Medical and Health Sciences, 1(2), 18-41, doi: https://doi.org/10.48185/smhs.v1i2.1225.
[35] Ginni, G. R., & Lade, S. C. (2025). A Learning-Based Ensemble Algorithm with Optimal Selection for Outlier Detection. Informatica, 49(14), doi: https://doi.org/10.31449/inf.v49i14.7439.
[36] Nur-A-Alam, M., Nasir, M. K., Ahsan, M., Based, M. A., Haider, J., & Kowalski, M. (2023). Ensemble classification of integrated CT scan datasets in detecting COVID-19 using feature fusion from contourlet transform and CNN. Scientific Reports, 13(1), 20063, doi: https://doi.org/10.1038/s41598-023-47183-9.
[37] Oladejo, A. O., Sch, J. W. M., Oluwabukunmi, F., Olufemi, D., McClure, J. W., Oladipo, K., ... & Lateef, A. Smart Spectrum Intelligence: AI-Guided Quantum Sensing in Terahertz-Enabled Broadband Networks, Volume 14–Issue 06, 181 – 206, 2025, ISSN: -2319–8656 doi: https://doi.org/10.7753/IJCATR1406.1012.
[38] Berahmand, K., Daneshfar, F., Salehi, E. S., Li, Y., & Xu, Y. (2024). Autoencoders and their applications in machine learning: a survey. Artificial intelligence review, 57(2), 28, doi: https://doi.org/10.1007/s10462-023-10662-6.
[39] Vishnu Shankar, S., Naffees Gowsar, S. R., & Manjubala, M. (2025). Variational Autoencoders (VAEs). In Revolution with Generative AI: Trends and Techniques (pp. 43-64). Cham: Springer Nature Switzerland, doi: https://doi.org/10.1007/978-3-031-91660-1_3.
[40] Chaudhary, A., Rastogi, R., Mattoo, A., Kumar, P., Kumari, T., & Dubey, D. (2025). Generative Adversarial Networks (GANs). Generative AI: Disruptive Technologies for Innovative Applications, 29-55, doi: https://doi.org/10.1002/9781394302932.ch2.
[41] Lagogiannis, I., Meissen, F., Kaissis, G., & Rueckert, D. (2023). Unsupervised pathology detection: a deep dive into the state of the art. IEEE transactions on medical imaging, 43(1), 241-252, doi: https://doi.org/10.1109/TMI.2023.3298093.
[42] Bekkair, A., Bellaouar, S., & Oulad-Naoui, S. (2025). Unsupervised graph attention autoencoder clustering-oriented for community detection in attributed networks. International Journal of Data Science and Analytics, 1-14, doi: https://doi.org/10.1007/s41060-025-00800-4.
[43] Tian, C., Zhang, F., & Wang, R. (2024). Adversarial regularized attributed network embedding for graph anomaly detection. Pattern Recognition Letters, 183, 111-116, doi: https://doi.org/10.1016/j.patrec.2024.05.004.
[44] Li, H., & Li, Y. (2023). Anomaly detection methods based on GAN: a survey. Applied Intelligence, 53(7), 8209-8231, doi: https://doi.org/10.1007/s10489-022-03905-6.
[45] Rajmohan, R., Kumar, T. A., Sandhya, S. G., & Hu, Y. C. (2024). R-GCN: A residual-gated recurrent unit convolution network model for anomaly detection in blockchain transactions. Multimedia Tools and Applications, 83(40), 87527-87551, doi: https://doi.org/10.1007/s11042-023-17942-x.
[46] Al-Tameemi, I. K. S., Feizi-Derakhshi, M. R., Pashazadeh, S., & Asadpour, M. (2024). A comprehensive review of visual–textual sentiment analysis from social media networks. Journal of Computational Social Science, 7(3), 2767-2838, doi: https://doi.org/10.1007/s42001-024-00326-y.
[47] Jain, S., & Sinha, A. (2023). TriBeC: identifying influential users on social networks with upstream and downstream network centrality. International Journal of General Systems, 52(3), 275-296, doi:
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
