Modeling and detecting change in temporal networks via the degree corrected stochastic block model

Wilson, James D.; Stevens, Nathaniel T.; Woodall, William H.

doi:10.1002/qre.2520

Cited by 58 publications

(115 citation statements)

References 75 publications

(107 reference statements)

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…One example of this approach uses the hierarchical random graph model [26]. A recent paper [47] discusses this approach with a degree-corrected stochastic block model (DCSBM) and statistical process monitoring of selected statistics of the model.…”

Section: Dynamic Network Structure and Change Detectionmentioning

confidence: 99%

“…Wilson et al [47] use a DCSBM for undirected graphs, along with a change detection strategy based on control charts.…”

Section: Degree-corrected Stochastic Block Modelmentioning

confidence: 99%

“…By doing so, the DCSBM can be rewritten in the exponential family form. Since the DCSBM is not the main objective of analysis in this paper, we leave out the detailed description of its properties, which can be found in the aforementioned papers [1,21,47].…”

Section: Degree-corrected Stochastic Block Modelmentioning

confidence: 99%

“…We first compare our approach to the work of Wilson et al [47], who apply statistical process monitoring to the sequence of maximum likelihood estimates of the stochastic block model parameters. We used the R code published by the authors to generate the network sequences.…”

Section: Comparison To Network Monitoringmentioning

confidence: 99%

“…We used the R code published by the authors to generate the network sequences. Wilson et al [47] evaluate the performance of their approach by estimating the average run length over 1000 simulations for each of the 6 scenarios. The first 4 deal with local and global intensity change, and local and global variability change, and are not tests for our approach because they lead to no change in the block structure.…”

Section: Comparison To Network Monitoringmentioning

confidence: 99%

See 4 more Smart Citations

Context‐aided analysis of community evolution in networks

Pallotta

Konjevod

Cadena

et al. 2017

Statistical Analysis

View full text Add to dashboard Cite

We are interested in detecting and analyzing global changes in dynamic networks (networks that evolve with time). More precisely, we consider changes in the activity distribution within the network, in terms of density (ie, edge existence) and intensity (ie, edge weight). Detecting change in local properties, as well as individual measurements or metrics, has been well studied and often reduces to traditional statistical process control. In contrast, detecting change in larger scale structure of the network is more challenging and not as well understood. We address this problem by proposing a framework for detecting change in network structure based on separate pieces: a probabilistic model for partitioning nodes by their behavior, a label‐unswitching heuristic, and an approach to change detection for sequences of complex objects. We examine the performance of one instantiation of such a framework using mostly previously available pieces. The dataset we use for these investigations is the publicly available New York City Taxi and Limousine Commission dataset covering all taxi trips in New York City since 2009. Using it, we investigate the evolution of an ensemble of networks under different spatiotemporal resolutions. We identify the community structure by fitting a weighted stochastic block model. We offer insights on different node ranking and clustering methods, their ability to capture the rhythm of life in the Big Apple, and their potential usefulness in highlighting changes in the underlying network structure.

show abstract

Section: Dynamic Network Structure and Change Detectionmentioning

confidence: 99%

“…Wilson et al [47] use a DCSBM for undirected graphs, along with a change detection strategy based on control charts.…”

Section: Degree-corrected Stochastic Block Modelmentioning

confidence: 99%

Section: Degree-corrected Stochastic Block Modelmentioning

confidence: 99%

Section: Comparison To Network Monitoringmentioning

confidence: 99%

Section: Comparison To Network Monitoringmentioning

confidence: 99%

See 3 more Smart Citations

Context‐aided analysis of community evolution in networks

Pallotta

Konjevod

Cadena

et al. 2017

Statistical Analysis

View full text Add to dashboard Cite

show abstract

Statistical methods for network surveillance

Jeske

Stevens

Tartakovsky

et al. 2018

Appl Stoch Models Bus & Ind

Self Cite

View full text Add to dashboard Cite

show abstract

Discussion of “Statistical methods for network surveillance”

Sengupta

Woodall

2018

Appl Stoch Models Bus & Ind

Self Cite

View full text Add to dashboard Cite

We appreciate the opportunity to discuss this interesting and thought-provoking paper. We agree with the authors that there is a growing interest in network surveillance with many important applications.In the context of network surveillance, we think it is important to distinguish between the case where the network is deterministic and the case where the network is random.The first case arises when the network itself (ie, the set of vertices/nodes and the set of edges/links) is considered to be fixed and deterministic, and some kind of traffic is being transmitted via the network links. The traffic flow being transmitted through each network link is considered to be a random observation from some statistical model, and the goal of network surveillance in this scenario is to detect whether the random traffic flow through the deterministic network has significantly deviated from normal or baseline conditions. Two of the three examples in the paper fall under this category, namely, monitoring network security and monitoring reliability of data networks. This general framework also includes a variety of interconnected systems beyond computer networks, for example, vehicular traffic on the interstate highway network or electric power transmission via the power grid network. The underlying principles of network surveillance from computer networks can therefore be extended to such networked systems.The second case arises when networks at different point of time are considered to be a time series of random observations from a statistical model, such as the degree corrected stochastic blockmodel in the authors' Section 5.3.2. In this case, the network structure itself is the observed sequence of random variables, and the goal of network surveillance is to detect whether the network structure has significantly deviated from normal or baseline conditions. Examples include email networks (ie, the Enron network from their Section 5), social media networks, and friendship networks.These two cases are inherently different in terms of the statistical framework and the objective of network surveillance. In the first case, the objective is to carry out surveillance on networks, whereas in the second case, the objective is to carry out surveillance of networks. The umbrella term network surveillance appears to include both cases, but we think it is better to distinguish between them, preferably by using different terms to describe the two cases. Perhaps, fixed network surveillance and random network surveillance would work.There are sampling issues with respect to any type of surveillance. For example, how often should the process be sampled? Over what time period should the data be aggregated? In the authors' Figure 2, the number of users is recorded at five-minute intervals. What was the justification for this frequency of sampling? Sampling at a high frequency can make modeling more difficult, whereas sampling at lower frequencies means that detection of anomalies may be unsuccessful or delayed. Zwetsloot and Woodall 1 discusse...

show abstract

Modeling and detecting change in temporal networks via the degree corrected stochastic block model

Cited by 58 publications

References 75 publications

Context‐aided analysis of community evolution in networks

Context‐aided analysis of community evolution in networks

Statistical methods for network surveillance

Discussion of “Statistical methods for network surveillance”

Contact Info

Product

Resources

About