Adapting Stochastic Block Models to Power-Law Degree Distributions

Qiao, Maoying; Yu, Jun; Bian, Wei; Li, Qiang; Tao, Dacheng

doi:10.1109/tcyb.2017.2783325

Cited by 22 publications

(20 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Power-law [16] with exponent γ roughly means that the probability that a given vertex in the network has k connections (in other words, it has degree k ) behaves like k − γ for large k if the total population size is large enough compared to k . [16] To construct this graph, to each individual we assigned a random number δ i , which is an exponentially distributed random variable of parameter λ (this parameter is related to the exponent γ), and we fix a positive parameter (this parameter is related to the average number of connections per individual). Each pair of individuals i, j has risky interaction with probability .…”

Section: Methodsmentioning

confidence: 99%

The role of connectivity on COVID-19 preventive approaches

Pina

Tóbiás

et al. 2021

Preprint

View full text Add to dashboard Cite

Preventive and modelling approaches to address the COVID-19 pandemic have been primarily based on the age or occupation, and often disregard the importance of the population contact structure and individual connectivity. To address this gap, we developed models that first incorporate the role of heterogeneity and connectivity and then can be expanded to make assumptions about demographic characteristics. Results demonstrate that variations in the number of connections of individuals within a population modify the impact of public health interventions such vaccination approaches. We conclude that the most effective vaccination strategy will vary depending on the underlying contact structure of individuals within a population and on timing of the interventions.

show abstract

Section: Methodsmentioning

confidence: 99%

The role of connectivity on COVID-19 preventive approaches

Pina

Tóbiás

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…DC-SBM [1] introduced a Poisson-valued degree parameter for each node to handle the heterogeneity of node degree, thus networks could be split into heterogeneous. The power-law degree SBM [13] explicitly encoded the power-law feature of networks from the perspective of Bernoulli distribution. Besides, Newman et al [11] developed a mixture model to explore the network structure, in which the nodes with the same link patterns were divided into the same groups.…”

Section: Related Workmentioning

confidence: 99%

“…Based on current research, the real-world complex networks usually demonstrate a variety of features, such as the scale-free property and node attributes [13], which are the key factors that should be considered in the community detection. Many works have shown that making full use of the attribute information of nodes with the topological structure can significantly improve community detection results and it can be used to depict community profiles and semantics [4,16].…”

Section: Introductionmentioning

confidence: 99%

“…It treated nodes within a group equally and ignored the heterogeneity. Furthermore, the DC-SBM [1] and the power-law degree SBM [13] were proposed to generate the observed network from the perspective of a single node, i.e. from node-level.…”

Section: Introductionmentioning

confidence: 99%

“…jointly encode the varying degree distribution and node multiple attributes to make them complement each other. Only considering one aspect [1,13], modeling network structure or node attributes [16] separately or treating the nodes within a group equally [4] limit the performance for community detection in real-world complex networks.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Unified Bayesian Model of Community Detection in Attribute Networks with Power-Law Degree Distribution

Zhang

Wang

et al. 2021

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Detecting community structure is an important research topic in complex network analysis. How to improve community detection results by using various features in the network is a very challenging problem. The scale-free and attributes of nodes are the two relatively independent aspects of the complex networks in the real world, the former is an inherent structural feature from the global perspective and the later can be used to significantly enhance community detection and community semantics. However, these two aspects are usually modeled and computed independently in previous methods. Based on that, we propose a novel unified Bayesian generative model which combines network topology and node attributes simultaneously to identify community structures via considering to model the scale-free feature. We propose the degree decay variable to preserve the power-law degree characteristic of the network. Specifically, this model composes of two closely correlated parts by a probabilistic transition matrix, one for network topology and the other for nodes attributes. Moreover, we develop a variational EM algorithm to optimize the objective function of the model. Experiments on synthetic and real networks show that our model has a better performance compared with some baselines on community detection in attribute networks.

show abstract

Stochastic Blockmodels Meets Overlapping Community Detection

Zhao

et al. 2020

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

It turns out that the Stochastic Blockmodel (SBM) and its variants can successfully accomplish a variety of tasks, such as discovering community structures. Note that the main limitations are inferencing high time complexity and poor scalability. Our effort is motivated by the goal of harnessing their complementary strengths to develop a scalability SBM for graphs, that also enjoys an efficient inference process and discovery interpretable communities. Unlike traditional SBM that each node is assumed to belong to just one block, we wish to use the node importance to also infer the community membership(s) of each node (as it is one of the goals of SBMs). To this end, we propose a multi-stage maximum likelihood strategy for inferring the latent parameters of adapting the Stochastic Blockmodels to Overlapping Community Detection (OCD-SBM). The intuitive properties to build the model, is more in line with the real-world network to reveal the hidden community structural characteristics. Particularly, this enables inference of not just the node's membership into communities, but the strength of the membership in each of the communities the node belongs to. Experiments conducted on various datasets verify the effectiveness of our model.

show abstract

Adapting Stochastic Block Models to Power-Law Degree Distributions

Cited by 22 publications

References 54 publications

The role of connectivity on COVID-19 preventive approaches

The role of connectivity on COVID-19 preventive approaches

A Unified Bayesian Model of Community Detection in Attribute Networks with Power-Law Degree Distribution

Stochastic Blockmodels Meets Overlapping Community Detection

Contact Info

Product

Resources

About