ارائه روشی جدید برای تشخیص گره‌های پرنفوذ در گراف شبکه‌های اجتماعی با استفاده از روش‌های یادگیری عمیق

نوع مقاله : مقاله پژوهشی (کاربردی)

نویسنده

عضو هیات علمی، گروه مهندسی کامپیوتر، دانشکده مهندسی برق و کامپیوتر، دانشگاه فنی و حرفه‌ای، تهران، ایران.

چکیده

یکی از مسائل مهم در شبکه­های اجتماعی بزرگ، شناسایی کاربران بانفوذ برای بیشینه­سازی انتشار اخبار و پیام­ها است که عموماً تحت عنوان مشکل بیشینه­سازی تأثیر در شبکه­های اجتماعی (مشکل SIM)، شناخته می‌شود. موفقیت روند ­انتشار در این شبکه­ها بستگی به مکانیسم انتخاب کاربران تأثیرگذار دارد. از طرفی با افزایش سرعت رشد و حجم داده­ها در گراف شبکه­های اجتماعی بزرگ یکی از معضلات اصلی، تعداد بسیار زیاد گره­ها و یال­هاست که انجام هر نوع پردازشی روی آن را با مشکلات متعدد روبه‌رو می­سازد. اجرای روش­های سنتی بر روی گراف­های بزرگ و دارای داده­های با ­ابعاد بالا، سخت و زمان‌بر است و باید روش­های مؤثرتری به‌کار گرفته شود. در این مقاله ما با استفاده از یادگیری عمیق، روش جدیدی برای کاهش ابعاد گراف شبکه‌های اجتماعی پیشنهاد داده و سپس با در نظر گرفتن حداقل هم‌پوشانی بین گره­ها تلاش می­کنیم تا راه‌حل جدید و مؤثری را برای مسئله بیشینه­سازی تأثیر ارائه دهیم. در ادامه نتایج حاصل از شبیه­سازی در دنیای واقعی، نشان‌دهنده عملکرد بهتر روش پیشنهادی از نظر زمان اجرا و میزان گسترش نفوذ نسبت به تکنیک‌های سنتی است. 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

A New Method for Detecting Influential Nodes in Social Network Graphs Using Deep Learning Techniques

نویسنده [English]

  • Azad Noori
Faculty Member, Department of Computer Engineering, Faculty of Electrical and Computer Engineering, Technical and Vocational University (TVU), Tehran, Iran.
چکیده [English]

One of the most important issues in large social networks is identifying influential users to maximize the diffusion of news and messages which is popularly known as the Social Influence Maximization Problem (SIM Problem). The success of the diffusion process in these networks depends on the influential users’ selection mechanism. On the other hand, with the increase in growth rate and data size in the graph of large social networks, one of the main challenges is the large number of nodes and edges which makes any processing problematic. Implementing traditional methods on large graphs with high-dimensional data is difficult and time consuming, and more efficient methods must be used. In this paper, a new method for reducing the graph size of social networks using deep learning is proposed, followed by providing a novel and effective solution to the Social Influence Maximization Problem by considering the minimum overlap between nodes. The findings of the simulation in the real world show better performance of the proposed method in terms of execution time and spread of influence than traditional techniques.

کلیدواژه‌ها [English]

  • Social networks
  • Complex graphs
  • Influence maximization
  • Deep learning
  • Sparse autoencoder

مراجع

[1] Centola, D. (2010). The spread of behavior in an online social network experiment. science, 329(5996), 1194-1197. https://doi.org/10.1126/science.1185231
[2] Chen, W., Wang, C., & Wang, Y. (2010, July 25-28). Scalable influence maximization for prevalent viral marketing in large-scale social networks. Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, Washington, DC, USA. https://doi.org/10.1145/1835804.1835934
[3] Bakshy, E., Hofman, J. M., Mason, W. A., & Watts, D. J. (2011, February 9-12). Everyone's an influencer: quantifying influence on twitter. Proceedings of the fourth ACM international conference on Web search and data mining, Hong Kong, China. https://doi.org/10.1145/1 935826.1935845
[4] Banerjee, S., Jenamani, M., & Pratihar, D. K. (2020). A survey on influence maximization in a social network. Knowledge and Information Systems, 62(9), 3417-3455. https://doi.org/1 0.1007/s10115-020-01461-4
[5] Li, Y., Fan, J., Wang, Y., & Tan, K. L. (2018). Influence Maximization on Social Graphs: A Survey. IEEE Transactions on Knowledge and Data Engineering, 30(10), 1852-1872. https://doi.org/10.1109/TKDE.2018.2807843
[6] Zareie, A., Sheikhahmadi, A., & Khamforoosh, K. (2018). Influence maximization in social networks based on TOPSIS. Expert Systems with Applications, 108, 96-107. https://doi.org/10.1016/j.eswa.2018.05.001
[7] Chandran, J., & Viswanatham, V. M. (2021, February 19-20). Evaluating the Effectiveness of Community Detection Algorithms for Influence Maximization in Social Networks. 2021 International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies  Bhilai, India https://doi.org/10.1109/ICAECT49130.2021.939 2387
[8] Kumar, S., Singhla, L., Jindal, K., Grover, K., & Panda, B. S. (2021). IM-ELPR: Influence maximization in social networks using label propagation based community structure. Applied Intelligence, 51(11), 7647-7665. https://doi.org/10.1007/s10489-021-02266-w
[9] Wang, Z., Sun, C., Xi, J., & Li, X. (2021). Influence maximization in social graphs based on community structure and node coverage gain. Future Generation Computer Systems, 118, 327-338. https://doi.org/10.1016/j.future.2021.01.025
[10] Statista. (2022). Leading countries based on Facebook audience size as of January 2022. Statista. https://www.statista.com/statistics/268136/top-15-countries-based-on-number-of -facebook-users/
[11] Rosvall, M., & Bergstrom, C. T. (2008). Maps of random walks on complex networks reveal community structure. Proceedings of the National Academy of Sciences, 105(4), 1118-1123. https://doi.org/10.1073/pnas.0706851105
[12] LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539
[13] Zhang, Y.,  Lyu, T., & Zhang, Y. (2018, February 2–7). COSINE: Community-Preserving Social Network Embedding From Information Diffusion Cascades. The Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana USA. https://ojs.aa ai.org/index.php/AAAI/article/view/11856
[14] Wikipedia. (2022, February 28). Complex network. the Creative Commons Attribution-ShareAlike License 3.0. https://en.wikipedia.org/wiki/Complex_network
[15] Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70-90. https://doi.org/10.1016/j.co mpag.2018.02.016
[16] Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., & ... (2016, June 19-24). Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin. Proceedings of The 33rd International Conference on Machine Learning, NewYork, United States. https:/ /proceedings.mlr.press/v48/amodei16.html
[17] Yang, H., Li, S., Wu, X., Lu, H., & Han, W. (2019). A Novel Solutions for Malicious Code Detection and Family Clustering Based on Machine Learning. IEEE Access, 7, 148853-148860. https://doi.org/10.1109/ACCESS.2019.2946482
[18] Zhao, D., Gao, B., Wang, Y., Wang, L., & Wang, Z. (2018). Optimal Dismantling of Interdependent Networks Based on Inverse Explosive Percolation. IEEE Transactions on Circuits and Systems II: Express Briefs, 65(7), 953-957. https://doi.org/10.1109/TCSII.2018.27 93257
[19] Collobert, R., & Weston, J. (2008, July 5-9). A unified architecture for natural language processing: deep neural networks with multitask learning. Proceedings of the 25th international conference on Machine learning, Helsinki, Finland. https://doi.org/10 .1145/1390156.1390177
[20] Li, S., Jiang, L., Wu, X., Han, W., Zhao, D., & Wang, Z. (2021). A weighted network community detection algorithm based on deep learning. Applied Mathematics and Computation, 401(7), 126012. https://doi.org/10.1016/j.amc.2021.126012
[21] Keikha, M. M., Rahgozar, M., Asadpour, M., & Abdollahi, M. F. (2020). Influence maximization across heterogeneous interconnected networks based on deep learning. Expert Systems with Applications, 140(10), 112905. https://doi.org/10.10 16/j.eswa.2019.112905
[22] Kitsak, M., Gallos, L. K., Havlin, S., Liljeros, F., Muchnik, L., Stanley, H. E., & Makse, H. A. (2010). Identification of influential spreaders in complex networks. Nature Physics, 6(11), 888-893. https://doi.org/10.1038/nphys1746
[23] Bao, Z-K., Liu, J-G., & Zhang, H-F. (2017). Identifying multiple influential spreaders by a heuristic clustering algorithm. Physics Letters A, 381(11), 976-983. https://doi.org/10.101 6/j.physleta.2017.01.043
[24] Guo, L., Lin, J-H., Guo, Q., & Liu, J-G. (2016). Identifying multiple influential spreaders in term of the distance-based coloring. Physics Letters A, 380(7-8), 837-842. https://doi.org/ 10.1016/j.physleta.2015.12.031
فصلنامه علمی کارافن
دوره 19، شماره 1 - شماره پیاپی 57
فنی و مهندسی
خرداد 1401
صفحه 607-628

فایل ها

سابقه مقاله

  • تاریخ دریافت: 27 مهر 1400
  • تاریخ بازنگری: 17 اسفند 1400
  • تاریخ پذیرش: 23 اسفند 1400

هم رسانی

ارجاع به این مقاله

آمار