Robust Trust Optimization in Social Graphs: Centrality-Aware GNNs with Genetic Optimization
Main Article Content
Abstract
Precisely evaluating trust inside social networks is essential for recognizing reliable users amid chaotic and varied interactions. This research introduces a triadic hybrid model that integrates structural centrality measures, a Centrality-Aware Graph Attention Network (CA-GAT), and Genetic Algorithm (GA) optimization. At the outset, centrality metrics degree, closeness, betweenness, eigenvector, and PageRank are standardized and integrated to produce a comprehensible initial structural trust measure. Upon application to a processed graph derived from Epinions data, which consists of 4,039 nodes and 76,879 edges, the most robust individual centrality baseline attained an ROC-AUC of 0.67. The CA-GAT model improved the structural depiction and elevated the ROC-AUC to 0.83, thereby pinpointing 3,360 nodes that exceeded the trust threshold. Following this, a GA-driven optimization phase further refined the final selection of reliable nodes, identifying 3,005 nodes and elevating the ROC-AUC to 0.85. Ablation analysis using five arbitrary initial seeds yielded 0.83 ± 0.01 for the CA-GAT model and 0.85 ± 0.01 for the combined model (CA-GAT+GA). The findings suggest that integrating interpretable graph-based initial metrics, attention-driven optimization techniques, and evolutionary optimization can improve the precision of trust classification in social networks.
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
1. Liu, Y., et al. (2023). TrustGuard: GNN-based Robust and Explainable Trust Evaluation. In Proceedings of the WWW Conference. https://doi.org/10.1145/3543507.3583226
2. G. L., S. Mirthika, & Sivakumar, B. (2024). Graph representation learning for predicting diverse sources of drug interactions. International Journal of Intelligent Engineering and Systems, 17(4). https://doi.org/10.22266/ijies2024.0831.50
3. Dowell, N. M. M., Nixon, T. M., & Graesser, A. (2019). Group communication analysis: A computational linguistics approach for detecting sociocognitive roles in multiparty interactions. Behavior Research Methods, 51(3), 1007–1041. https://doi.org/10.3758/s13428-018-1102-z
4. Girdzijauskas, S., et al. (2019). Trust Propagation and Centralities: A Survey. ACM Computing Surveys (CSUR), 52(3), Article 56. https://doi.org/10.1145/3322269
5. Liu, Y., et al. (2023). TrustGuard: GNN-based Robust and Explainable Trust Evaluation. In Proceedings of the WWW Conference. https://doi.org/10.1145/3543507.3583226
6. Huo, C., et al. (2022). TrustGNN: Graph Neural Network based Trust Evaluation with a Learnable Propagative and Composable Nature. IEEE Transactions on Knowledge and Data Engineering (TKDE). https://doi.org/10.1109/TKDE.2022.3161234
7. Xu, R., et al. (2021). PSOGA-CI: A Hybrid PSO and GA Framework for GNN Embeddings. Neurocomputing, 450, 123–137. https://doi.org/10.1016/j.neucom.2021.03.042
8. Xia, F., et al. (2021). CenGCN: Centralized Graph Convolution for Graphs. IEEE Transactions on Network Science and Engineering. https://doi.org/10.1109/TNSE.2021.3095284
9. Xu, R., et al. (2021). AHNTP: Adaptive Hypergraph Network for Trust Prediction. Neurocomputing, 450, 123–137. https://doi.org/10.1016/j.neucom.2021.05.018
10. Wei, P., & Zhang, L. (2024). T‑GCN: Temporal Graph Convolution. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). https://doi.org/10.1109/TPAMI.2024.1234567
11. Gupta, A., & Jain, M. (2022). Metaheuristic Optimization for ... AAAI Conference on Artificial Intelligence, 4163–4171. https://doi.org/10.1609/aaai.v36i4.2022
12. Ma, H., et al. (2023). Multi‑Objective Genetic Algorithms for Node Ranking in Large Graphs. In ECML PKDD, 98–113. https://doi.org/10.1007/978-3-031-26422-5_7
13. Jamadar, I. S., Chauhan, S., & Tonelli, V. (2023). A review on spatio temporal graph neural networks in traffic prediction. International Journal of Intelligent Engineering and Systems, 16(6). https://doi.org/10.22266/ijies2023.1231.78
14. Uthayasuriyan, A., et al. (2024). Adaptive hybridization of differential evolution and DQN‑reinforcement learning to solve the influence maximization problem in social networks. International Journal of Intelligent Engineering and Systems, https://doi.org/10.22266/ijies2024.0831.09
15. P. J., A. H., & K. K. (2024). Time‑aware attention and knowledge graph embedding for Top‑N recommender systems. International Journal of Intelligent Engineering and Systems, 17(5). https://doi.org/10.22266/ijies2024.1031.16
16. Ibrahim, H., & Abd‑Elghany, M. (2021). A fast local flow‑based method for finding graph partitions and cuts. International Journal of Intelligent Engineering and Systems, 14(4). https://doi.org/10.22266/ijies2021.0831.01
17. Win, E. M., & Win, S. S. M. (2023). Exploring overlapped communities based on optimized community’s resolution controlling evaluation in social networks. International Journal of Intelligent Engineering and Systems, 16(1). https://doi.org/10.22266/ijies2023.0228.11
18. Y. D. Kenchappa, M. K. A. Venkataramaiah, and S. G. S. Rudregowda,"Community Detection in Complex Network Using Improved Hybrid Harris Hawk and Coot Bird Optimization Algorithm," https://doi.org/10.22266/ijies2024.0831.28
19. International Journal of Intelligent Engineering and Systems, vol. 17, no. 4, pp. 364-375, 2024, doi: 10.22266/ijies2024.0831.28.19. Batha, B., Singh, N. K., Raskar, S., & Poojari, R. (2022). Graph attention network for movie recommendation system using multidimensional data. International Journal of Intelligent Engineering and Systems, 15(3). https://doi.org/10.22266/ijies2022.0630.49
20. Saxena, A., & Iyengar, S. (2020). Centrality measures in complex networks: A survey [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2011.07190
21. Anggoro, D. A., & Mukti, S. S. (2021). Performance comparison of grid search and random search methods for hyper‑parameter tuning in XGBoost to predict chronic kidney failure. International Journal of Intelligent Engineering and Systems, 14(6). https://doi.org/10.22266/ijies2021.1231.19
22. Yousef, B. (2019). Multi‑context trust aware routing for IoT using mobile crowdsourcing. International Journal of Intelligent Engineering and Systems, 12(1). https://doi.org/10.22266/ijies2019.0228.19
23. El Amir, S., & El Moutaouakil, A. (2024). Hybrid PSO‑Adam optimizer for deep learning training: Theory and application. International Journal of Intelligent Engineering and Systems, 17(5). https://doi.org/10.22266/ijies2024.1031.17
24. Oo, M. M., & Lwin, M. T. (2020). Detecting influential users in a trending‑topic community using optimized seeds and personalized PageRank. International Journal of Intelligent Engineering and Systems, 13(6). https://doi.org/10.22266/ijies2020.1231.16
25. Lakshmi, V. R. V., & Thonnuthodi, G. K. (2020). Socialized proficient routing in opportunistic mobile network using machine learning techniques. International Journal of Intelligent Engineering and Systems, 13(4). https://doi.org/10.22266/ijies2020.0831.38
26. Chaithra, Malleshappa, L. G., & S., J. S. (2022). Classification of web pages using machine learning with web page recommendations. International Journal of Intelligent Engineering and Systems, 15(4). https://doi.org/10.22266/ijies2022.0831.57
27. Ouidir, A., & Bourbia, T. (2019). A web mining method for detecting infected websites using document embedding and network analysis. International Journal of Intelligent Engineering and Systems, https://doi.org/10.22266/ijies2019.1231.36