Statistical Inference for Social Networks: Maximum Likelihood Estimation in Stochastic Block Models
DOI:
https://doi.org/10.61173/stecep16112Keywords:
Maximum likelihood estimation, stochastic block model, social network analysis, community detection, link predictionAbstract
Social network data are useful because they record visible relationships, and they can also show social structures that cannot be directly observed. This paper discusses maximum likelihood estimation (MLE) in stochastic block models (SBMs), which provides a statistical method for studying these hidden structures. In an SBM, users are placed into hidden communities, and the probability of a link depends on the communities to which the two users belong. MLE can then estimate the hidden community labels and the edge probabilities between different groups by using observed network data. The paper first explains the basic ideas of MLE and SBM, and it then discusses the use of this method in community detection, link prediction, user grouping, and recommendation. The discussion also explains that the basic SBM is usually too simple for real social networks. Overall, MLE and SBM provide a relatively clear way to connect visible social links with hidden social patterns.
References
Singh S S, Muhuri S, Mishra S, et al. Social network analysis: A survey on process, tools, and application. ACM Computing Surveys, 2024, 56(8): 1-39.
Jin D, Yu Z, Jiao P, et al. A survey of community detection approaches: From statistical modeling to deep learning. IEEE Transactions on Knowledge and Data Engineering, 2021, 35(2): 1149-1170.
Blondel V, Guillaume J L, Lambiotte R. Fast unfolding of communities in large networks: 15 years later. Journal of Statistical Mechanics: Theory and Experiment, 2024, 2024(10): 10R001.
Nair L S, Jayaraman S, Krishna Nagam S P. An improved link prediction approach for directed complex networks using stochastic block modeling. Big Data and Cognitive Computing, 2023, 7(1): 31.
Myung I J. Tutorial on maximum likelihood estimation. Journal of Mathematical Psychology, 2003, 47(1): 90-100.
De Nicola G, Sischka B, Kauermann G. Mixture models and networks: The stochastic blockmodel. Statistical Modelling, 2022, 22(1-2): 67-94.
Huang S, Sun J, Feng Y. PCABM: Pairwise covariates-adjusted block model for community detection. Journal of the American Statistical Association, 2024, 119(547): 2092-2104.
Mohamed M S, Nguyen D, Vullikanti A, et al. Differentially private community detection for stochastic block models. In International Conference on Machine Learning. PMLR, 2022: 15858-15894.
Amini A, Paez M, Lin L. Hierarchical stochastic block model for community detection in multiplex networks. Bayesian Analysis, 2024, 19(1): 319-345.
Wang H, Le Z. Seven-layer model in complex networks link prediction: A survey. Sensors, 2020, 20(22): 6560.
Ahn J, Elmahdy A, Mohajer S, et al. On the fundamental limits of matrix completion: Leveraging hierarchical similarity graphs. IEEE Transactions on Information Theory, 2023, 70(3): 2039-2075.
Duchemin Q. Reliable prediction in the Markov stochastic block model. ESAIM: Probability and Statistics, 2023, 27: 80-135.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
