Change detection in a dynamic stream of attributed networks

Gahrooei, Mostafa Reisi; Paynabar, Kamran

doi:10.1080/00224065.2018.1507558

Cited by 27 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This fact has been recently stated by Reisi-Gharoei and Peynabar [24] for attributed social networks in which autocorrelations of data have been addressed for which Extended Kalman Filter (EKF) is used for parameters estimation.…”

mentioning

confidence: 83%

Monitoring Attributed Social Networks Based on Count Data and Random Effects

et al. 2020

View full text Add to dashboard Cite

This paper presents a novel approach for the statistical monitoring of online social networks where the edges represent the count of communications between ties at each time stamp. Since the available methods in the literature are limited to the assumption that the set of all interacting individuals is fixed during the monitoring horizon and their corresponding attributes do not change over time, the proposed method tackles these limitations due to the properties of the random effect concepts. Applying appropriate parameters estimation technique involved in a likelihood ratio testing (LRT) approach considering two different statistics, the longitudinal network data are monitored. The performance of the proposed method is verified using numerical examples including simulation studies as well as an illustrative example.

show abstract

mentioning

confidence: 83%

Monitoring Attributed Social Networks Based on Count Data and Random Effects

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Gahrooei and Paynabar () use a probabilistic model based approach to detect global structural changes occurring in a dynamic attributed network. They model each static attributed graph using a generalized linear model (GLM), where the probability of an edge between two vertices is defined as a function of the categorical attributes attached to them.…”

Section: Categorization Of Methodsmentioning

confidence: 99%

Change detection in dynamic attributed networks

Hewapathirana

2018

WIREs Data Min & Knowl

View full text Add to dashboard Cite

A network provides powerful means of representing complex relationships between entities by abstracting entities as vertices, and relationships as edges connecting vertices in a graph. Beyond the presence or absence of relationships, a network may contain additional information that can be attributed to the entities and their relationships. Attaching these additional attribute data to the corresponding vertices and edges yields an attributed graph. Moreover, in the majority of real‐world applications, such as online social networks, financial networks and transactional networks, relationships between entities evolve over time. Change detection in dynamic attributed networks is an important problem in many areas, such as fraud detection, cyber intrusion detection, and health care monitoring. It is a challenging problem because it involves a time sequence of attributed graphs, each of which is usually very large and can contain many attributes attached to the vertices and edges, resulting in a complex, high‐dimensional mathematical object. In this survey we provide an overview of some of the existing change detection methods that utilize attribute information. We categorize these methods based on the levels of structure in the graph that are exploited to detect changes. These levels are vertices, edges, subgraphs, communities, and the overall graph. We focus attention on the strengths and weaknesses of these methods, including their performance and scalability. Furthermore, we discuss some publicly available dynamic network datasets and give a brief overview of models to generate dynamic attributed networks. Finally, we discuss the limitations of existing approaches identifying key areas for future research. This article is categorized under: Fundamental Concepts of Data and Knowledge > Data Concepts Algorithmic Development > Spatial and Temporal Data Mining Technologies > Machine Learning Application Areas > Business and Industry

show abstract

“…A new modeling and change detection methodology for attributed network streams that exhibit intrinsic dynamic behavior is proposed by Gahrooei and Paynabar. 21 They integrated the generalized linear model (GLM) used for static modeling of attributed networks with state transition models that capture the dynamic behavior of network streams. The integrated model was updated over time using the extended Kalman filter along with an EWMA control chart for quick detection of abrupt changes.…”

Section: Network Model-based Monitoring Plansmentioning

confidence: 99%

“…Fotuhi et al 20 also modeled counts of communications among people using Poisson regression profiles and utilized extended Hoteling T 2 , F , and a standardized LRT method to detect step changes, drifts, and outliers in the parameters of the fitted Poisson regression profiles. A new modeling and change detection methodology for attributed network streams that exhibit intrinsic dynamic behavior is proposed by Gahrooei and Paynabar 21 . They integrated the generalized linear model (GLM) used for static modeling of attributed networks with state transition models that capture the dynamic behavior of network streams.…”

Section: Introductionmentioning

confidence: 99%

A nonparametric change detection approach in social networks

Hazrati‐Marangaloo

Noorossana

2021

Quality & Reliability Eng

View full text Add to dashboard Cite

A network provides powerful means of representing relationships between entities in complex physical, biological, cyber, and social systems. Any phenomena in those areas may be realized as changes in the structure of the associated networks. Hence, change detection in dynamic networks is an important problem in many areas, such as fraud detection, cyber intrusion detection, and health care monitoring. This article proposes a new methodology for monitoring dynamic networks for quick detection of structural changes in network streams and also estimating the location of the change-point. The proposed methodology utilizes the eigenvalues for the adjacency matrices of network snapshots and employs a nonparametric hypothesis to test if the distribution of the eigenvalues for the current snapshot is different from those of the previous ones along a sliding window of reference networks. The statistic of the nonparametric test, energy distance among eigenvalues, is monitored using a one-sided exponentially weighted moving average control chart. Then, after an anomaly detection signal from the monitoring scheme, eigenvalues for the snapshots are employed to calculate the energy statistic at various time steps to locate the change-point.The proposed method is intended to detect two types of structural changes in the networks: (1) change in the communication rates among individuals and (2) change in the community structure of the network. The proposed methodology is applied to both simulated and real-world data. Results indicate that the proposed methodology provides a reliable tool for monitoring networks streams and also estimating change-points locations for precise assessing of the networks under investigation.

show abstract

Change detection in a dynamic stream of attributed networks

Cited by 27 publications

References 34 publications

Monitoring Attributed Social Networks Based on Count Data and Random Effects

Monitoring Attributed Social Networks Based on Count Data and Random Effects

Change detection in dynamic attributed networks

A nonparametric change detection approach in social networks

Contact Info

Product

Resources

About