Abstract
Dynamic community detection has become a hot spot of researches, which helps detect the revolving relationships of complex systems. In view of the great value of dynamic community detection, various kinds of dynamic algorithms come into being. Deep learning-based algorithms, as one of the most popular methods, transfer the core ideas of feature representation to dynamic community detection in order to improve the accuracy of dynamic community detection. However, when committing feature aggregation strategies, most of methods focus on the attribute features but omit the structural information of networks, which lowers the accuracy of dynamic community detection. Also, the differences of learned features between adjacent time steps may be large, which does not correspond with the real world. In this paper, we utilize the node relevancy to measure the varying importance of different nodes, which reflects the structural information of networks. Having acquired the node representations at each time step, the cross entropy is used to smoothen adjacent time steps so that the differences between adjacent time steps can be small. Some extensive experiments on both the real-world datasets and synthetic datasets show that our algorithm is more superior than other algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sun, Y., Mburu, L., Wang, S.: Analysis of community properties and node properties to understand the structure of the bus transport network. Physica A 450, 523–530 (2016)
Gao, C., Su, Z., Liu, J., Kurths, J.: Even central users do not always drive information diffusion. Commun. ACM 62(2), 61–67 (2019)
Li, J., Guo, J.: A new feature extraction algorithm based on entropy cloud characteristics of communication signals. Math. Probl. Eng. 2015, 1–8 (2015)
Lerner, B., Guterman, H., Aladjem, M., Dinstein, I.H.: A comparative study of neural network based feature extraction paradigms. Pattern. Recogn. Lett. 20(1), 7–14 (1999)
Shu, C., Ding, X., Fang, C.: Histogram of the oriented gradient for face recognition. Tsinghua Sci. Technol. 16(2), 216–224 (2011)
Mao, J., Jain, A.K.: Artificial neural networks for feature extraction and multivariate data projection. IEEE Trans. Neural Netw. 6(2), 296–317 (1995)
Du, N., Jia, X., Gao, J., Gopalakrishnan, V., Zhang, A.: Tracking temporal community strength in dynamic networks. IEEE Trans. Knowl. Data Eng. 27(11), 3125–3137 (2015)
Kuhn, F., Oshman, R.: Dynamic networks: models and algorithms. ACM Sigact. News 42(1), 82–96 (2011)
Wang, C., Deng, Y., Li, X., Chen, J., Gao, C.: Dynamic community detection based on a label-based swarm intelligence. IEEE Access 7, 161641–161653 (2019)
Xu, T., Zhang, Z., Philip, S.Y., Long, B.: Evolutionary clustering by hierarchical dirichlet process with hidden Markov state. In: Proceedings of the 8th IEEE International Conference on Data Mining (DMIN), pp. 658–667 (2008)
Gao, C., Liang, M., Li, X., Zhang, Z., Wang, Z., Zhou, Z.: Network community detection based on the physarum-inspired computational framework. IEEE ACM T. Comput. Bi. 15(6), 1916–1928 (2016)
Wang, H., et al.: Medication combination prediction using temporal attention mechanism and simple graph convolution. IEEE J. Biomed. Health Inform. (2021). https://doi.org/10.1109/JBHI.2021.3082548
Taguchi, H., Liu, X., Murata, T.: Graph convolutional networks for graphs containing missing features. Future Gener. Comput. Syst. 117, 155–168 (2021)
Song, W., Xiao, Z., Wang, Y., Charlin, L., Zhang, M., Tang, J.: Session-based social recommendation via dynamic graph attention networks. In: Proceedings of the 12th ACM International Conference on Web Search and Data Mining (WSDM), pp. 555–563 (2019)
Benesty, J., Chen, J., Huang, Y., Cohen, I.: Pearson correlation coefficient. In: Noise Reduction in Speech Processing, pp. 1–4 (2009)
Ma, X., Dong, D.: Evolutionary nonnegative matrix factorization algorithms for community detection in dynamic networks. IEEE Trans. Knowl. Data Eng. 29(5), 1045–1058 (2017)
Mucha, P.J., Richardson, T., Macon, K., Porter, M.A., Onnela, J.P.: Community structure in time-dependent, multiscale, and multiplex networks. Science 328(5980), 876–878 (2010)
Liu, F., Wu, J., Xue, S., Zhou, C., Yang, J., Sheng, Q.: Detecting the evolving community structure in dynamic social networks. World Wide Web 23(2), 715–733 (2019). https://doi.org/10.1007/s11280-019-00710-z
Zhang, Z., Cui, P., Pei, J., Wang, X., Zhu, W.: Timers: error-bounded SVD restart on dynamic networks. In: 32nd Proceedings of the AAAI Conference on Artificial Intelligence(AAAI), pp. 224–231 (2018)
Acknowledgment
Prof. Chao Gao and Dr. Li Tao are corresponding authors of this paper. This work was supported by the National Key R&D Program of China (No. 2019YFB2102300), National Natural Science Foundation of China (Nos. 61976181, 11931015, 61762020), Fok Ying-Tong Education Foundation, China (No. 171105), Key Technology Research and Development Program of Science and Technology Scientific and Technological Innovation Team of Shaanxi Province (No. 2020TD-013) and National Municipal Training Program of Innovation and Entrepreneurship for Undergraduates (No. 202010635053).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, F., Zhu, J., Luo, Z., Wang, Z., Tao, L., Gao, C. (2021). Community Detection in Dynamic Networks: A Novel Deep Learning Method. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, SY. (eds) Knowledge Science, Engineering and Management. KSEM 2021. Lecture Notes in Computer Science(), vol 12815. Springer, Cham. https://doi.org/10.1007/978-3-030-82136-4_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-82136-4_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82135-7
Online ISBN: 978-3-030-82136-4
eBook Packages: Computer ScienceComputer Science (R0)