Communication networks, such as social and collaborative networks, are characterized by a highly dynamic, constantly changing environment. This makes the analysis of such networks, such as the formation of communities, challenging. The adaptive temporal graph neural network (AT-GNN) was introduced here to overcome these challenges by incorporating temporal segmentation, feature extraction, and attention mechanisms. Based on two large-scale datasets, the Stanford Network Analysis Project (SNAP) and the Digital Bibliography and Library Project (DBLP), the AT-GNN model considers structural and temporal features for predicting community behaviors. Temporal segmentation was done through clustering while using node and edge attribute extraction. The preprocessing stage involved embedding layers, attention mechanisms, and recurrent layers. These components enabled the AT-GNN model to adjust the weight of essential relationships through dynamic networks, enhancing the explainability of community changes. A comparison was made between the proposed model and best-performing models, showing improved predictive accuracy of 98%, precision of 92%, recall of 95%, and F1-score of 93%. This work emphasizes the scalability, flexibility, and dynamism of the AT-GNN model and offers a starting point for studying dynamic systems. Future work will extend to graphs in continuous time and to enormously large networks, improving the model's effectiveness in real-time dynamic networks. These developments highlight the applicability of AT-GNN in various real-world settings, such as social, biological, and organizational networks.
Citation: Yongyan Zhao, Jian Li. Integrating artificial intelligence with network evolution theory for community behavior prediction in dynamic complex systems[J]. AIMS Mathematics, 2025, 10(2): 2042-2063. doi: 10.3934/math.2025096
Communication networks, such as social and collaborative networks, are characterized by a highly dynamic, constantly changing environment. This makes the analysis of such networks, such as the formation of communities, challenging. The adaptive temporal graph neural network (AT-GNN) was introduced here to overcome these challenges by incorporating temporal segmentation, feature extraction, and attention mechanisms. Based on two large-scale datasets, the Stanford Network Analysis Project (SNAP) and the Digital Bibliography and Library Project (DBLP), the AT-GNN model considers structural and temporal features for predicting community behaviors. Temporal segmentation was done through clustering while using node and edge attribute extraction. The preprocessing stage involved embedding layers, attention mechanisms, and recurrent layers. These components enabled the AT-GNN model to adjust the weight of essential relationships through dynamic networks, enhancing the explainability of community changes. A comparison was made between the proposed model and best-performing models, showing improved predictive accuracy of 98%, precision of 92%, recall of 95%, and F1-score of 93%. This work emphasizes the scalability, flexibility, and dynamism of the AT-GNN model and offers a starting point for studying dynamic systems. Future work will extend to graphs in continuous time and to enormously large networks, improving the model's effectiveness in real-time dynamic networks. These developments highlight the applicability of AT-GNN in various real-world settings, such as social, biological, and organizational networks.
| [1] | M. Pósfai, A. L. Barabási, Network science, Cambridge: Cambridge University Press, 2016. |
| [2] |
S. Fortunato, D. Hric, Community detection in networks: A user guide, Phys. Rep., 659 (2016), 1–44. https://doi.org/10.1016/j.physrep.2016.09.002 doi: 10.1016/j.physrep.2016.09.002
|
| [3] |
Y. Wu, L. Pan, LSTEG: An evolutionary game model leveraging deep reinforcement learning for privacy behavior analysis on social networks, Inform. Sciences, 2024, 120842. https://doi.org/10.1016/j.ins.2024.120842 doi: 10.1016/j.ins.2024.120842
|
| [4] |
W. Jiang, J. Luo, Graph neural network for traffic forecasting: A survey, Expert Syst. Appl., 207 (2022), 117921. https://doi.org/10.1016/j.eswa.2022.117921 doi: 10.1016/j.eswa.2022.117921
|
| [5] |
P. Holme, J. Saramäki, Temporal networks, Phys. Rep., 519 (2012), 97–125. https://doi.org/10.1016/j.physrep.2012.03.001 doi: 10.1016/j.physrep.2012.03.001
|
| [6] |
G. Rossetti, R. Cazabet, Community discovery in dynamic networks: A survey, ACM Comput. Surv., 51 (2018), 1–37. https://doi.org/10.1145/3172867 doi: 10.1145/3172867
|
| [7] |
Z. Qiu, Y. Yin, Y. Yuan, Y. Chen, Research on credit regulation mechanism of E-commerce platform based on evolutionary game theory, J. Syst. Sci. Syst. Eng., 2024, 1–30. https://doi.org/10.1007/s11518-024-5603-2 doi: 10.1007/s11518-024-5603-2
|
| [8] |
A. L. Barabási, R. Albert, Emergence of scaling in random networks, Science, 286 (1999), 509–512. https://doi.org/10.1126/science.286.5439.509 doi: 10.1126/science.286.5439.509
|
| [9] |
P. Holme, B. J. Kim, Growing scale-free networks with tunable clustering, Phys. Rev. E, 65 (2002), 026107. https://doi.org/10.1103/PhysRevE.65.026107 doi: 10.1103/PhysRevE.65.026107
|
| [10] |
A. L. Barabási, Z. N. Oltvai, Network biology: Understanding the cell's functional organization, Nat. Rev. Gene., 5 (2004), 101. https://doi.org/10.1038/nrg1272 doi: 10.1038/nrg1272
|
| [11] | M. A. Saidu, L. S. Shamsudeen, A. K. Muhammad, A. Abdulkadir, Exploring E-commerce opportunities for a better international trading and tax revenue generation: A review for developing countries, J. Sci. Technol. Educ., 10 (2022), 109–24. |
| [12] |
Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, S. Y. Philip, A comprehensive survey on graph neural networks, IEEE T. Neur. Net. Lear., 32 (2020), 4–24. https://doi.org/10.1109/TNNLS.2020.2978386 doi: 10.1109/TNNLS.2020.2978386
|
| [13] |
P. Goyal, S. R. Chhetri, A. Canedo, Dyngraph2vec: Capturing network dynamics using dynamic graph representation learning, Knowl.-Based Syst., 187 (2020), 104816. https://doi.org/10.1016/j.knosys.2019.06.024 doi: 10.1016/j.knosys.2019.06.024
|
| [14] |
L. Akoglu, H. Tong, D. Koutra, Graph-based anomaly detection and description: A survey, Data Min. Knowl. Disc., 29 (2015), 626–688. https://doi.org/10.1007/s10618-014-0365-y doi: 10.1007/s10618-014-0365-y
|
| [15] |
Y. Jiang, B. Ma, X. Wang, G. Yu, P. Yu, Z. Wang, et al., Blockchained federated learning for internet of things: A comprehensive survey, ACM Comput. Surv., 56 (2024), 1–37. https://doi.org/10.1145/3659099 doi: 10.1145/3659099
|
| [16] |
A. A. Beni, A. Esmaeili, Biosorption, an efficient method for removing heavy metals from industrial effluents: A Review, Environ. Technol. Inno., 17 (2020), 100503. https://doi.org/10.1016/j.eti.2019.100503 doi: 10.1016/j.eti.2019.100503
|
| [17] |
M. McPherson, L. S. Lovin, J. M. Cook, Birds of a feather: Homophily in social networks, Annu. Rev. Sociol., 27 (2001), 415–444. https://doi.org/10.1146/annurev.soc.27.1.415 doi: 10.1146/annurev.soc.27.1.415
|
| [18] |
P. Holme, J. Saramaki, Temporal networks, Phys. Rep., 519 (2012), 97–125. https://doi.org/10.1016/j.physrep.2012.03.001 doi: 10.1016/j.physrep.2012.03.001
|
| [19] |
G. Rossetti, M. Stella, R. Cazabet, K. Abramski, E. Cau, S. Citraro, et al., Y Social: An LLM-powered social media digital twin, arXiv Preprint, 2024. https://doi.org/10.48550/arXiv.2408.00818 doi: 10.48550/arXiv.2408.00818
|
| [20] |
D. C. Nguyen, Q. V. Pham, P. N. Pathirana, M. Ding, A. Seneviratne, Z. Lin, et al., Federated learning for smart healthcare: A survey, ACM Comput. Surv., 55 (2022), 1–37. https://doi.org/10.1145/3501296 doi: 10.1145/3501296
|
| [21] | L. Cai, Z. Chen, C. Luo, J. Gui, J. Ni, D. Li, et al., Structural temporal graph neural networks for anomaly detection in dynamic graphs, In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021, 3747–3756. https://doi.org/10.1145/3459637.3481955 |
| [22] |
X. Zhu, Y. Zhang, H. Ying, H. Chi, G. Sun, L. Zeng, Modeling epidemic dynamics using graph attention-based spatial temporal networks, Plos one, 19 (2024), e0307159. https://doi.org/10.1145/3459637.3481955 doi: 10.1145/3459637.3481955
|
| [23] |
H. Taherdoost, M. Madanchian, AI advancements: Comparison of innovative techniques, AI, 5 (2023), 38–54. https://doi.org/10.3390/ai5010003 doi: 10.3390/ai5010003
|
| [24] | D. Jin, Z. Yu, P. Jiao, S. Pan, D. He, J. Wu, et al., A survey of community detection approaches: From statistical modeling to deep learning, IEEE T. Knowl. Data Eng., 35 (2021), 1149–1170. |
| [25] | J. L. A. A. Krevl. Stanford Network Analysis Project, Available from: http://snap.stanford.edu/data. |
| [26] | M. Ley. Digital Bibliography and Library Project, Available from: https://dblp.org/. |
| [27] |
S. Min, Z. Gao, J. Peng, L. Wang, K. Qin, B. Fang, STGSN—a spatial-temporal graph neural network framework for time-evolving social networks, Knowl.-Based Syst., 214 (2021), 106746. https://doi.org/10.1016/j.knosys.2021.106746 doi: 10.1016/j.knosys.2021.106746
|
| [28] |
Y. R. Lin, Y. Chi, S. Zhu, H. Sundaram, B. L. Tseng, Analyzing communities and their evolutions in dynamic social networks, ACM T. Knowl. Discov. D., 3 (2009), 1–31. https://doi.org/10.1145/1514888.1514891 doi: 10.1145/1514888.1514891
|
Figures(6) / Tables(4)
Yongyan Zhao, Jian Li. Integrating artificial intelligence with network evolution theory for community behavior prediction in dynamic complex systems[J]. AIMS Mathematics, 2025, 10(2): 2042-2063. doi: 10.3934/math.2025096
DownLoad: