Advances in network clustering and blockmodeling

Provides an overview of the developments and advances in the field of network clustering and blockmodeling over the last 10 yearsThis book offers an integrated treatment of network clustering and blockmodeling, covering all of the newest approaches and methods that have been developed over the last...

Full description

Saved in:
Bibliographic Details
Main Authors: Doreian, Patrick, Batagelj, Vladimir, Ferligoj, Anuška
Format: eBook Book
Language:English
Published: Hoboken, NJ Wiley 2020
John Wiley & Sons, Incorporated
Wiley-Blackwell
Edition:1
Series:Wiley series in computational and quantitative social science
Subjects:
Social networks
Social networks > Mathematical models
Sociometry
ISBN:9781119224709, 1119224705
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 3.6.1 Software Support -- 3.7 Some Examples -- 3.7.1 The US Geographical Data, 2016 -- 3.7.2 Citations Among Authors from the Network Clustering Literature -- 3.8 Conclusion -- Acknowledgements -- References -- Chapter 4 Different Approaches to Community Detection -- 4.1 Introduction -- 4.2 Minimizing Constraint Violations: the Cut‐based Perspective -- 4.3 Maximizing Internal Density: the Clustering Perspective -- 4.4 Identifying Structural Equivalence: the Stochastic Block Model Perspective -- 4.5 Identifying Coarse‐grained Descriptions: the Dynamical Perspective -- 4.6 Discussion -- 4.7 Conclusions -- Acknowledgements -- References -- Chapter 5 Label Propagation for Clustering -- 5.1 Label Propagation Method -- 5.1.1 Resolution of Label Ties -- 5.1.2 Order of Label Propagation -- 5.1.3 Label Equilibrium Criterium -- 5.1.4 Algorithm and Complexity -- 5.2 Label Propagation as Optimization -- 5.3 Advances of Label Propagation -- 5.3.1 Label Propagation Under Constraints -- 5.3.2 Label Propagation with Preferences -- 5.3.3 Method Stability and Complexity -- 5.4 Extensions to Other Networks -- 5.5 Alternative Types of Network Structures -- 5.5.1 Overlapping Groups of Nodes -- 5.5.2 Hierarchy of Groups of Nodes -- 5.5.3 Structural Equivalence Groups -- 5.6 Applications of Label Propagation -- 5.7 Summary and Outlook -- References -- Chapter 6 Blockmodeling of Valued Networks -- 6.1 Introduction -- 6.2 Valued Data Types -- 6.3 Transformations -- 6.3.1 Scaling Transformations -- 6.3.2 Dichotomization -- 6.3.3 Normalization Procedures -- 6.3.4 Iterative Row‐column Normalization -- 6.3.5 Transaction‐flow and Deviational Transformations -- 6.4 Indirect Clustering Approaches -- 6.4.1 Structural Equivalence: Indirect Metrics -- 6.4.2 The CONCOR Algorithm -- 6.4.3 Deviational Structural Equivalence: Indirect Approach
  • Cover -- Title Page -- Copyright -- Brief Contents -- Contents -- List of Contributors -- Chapter 1 Introduction -- 1.1 On the Chapters -- 1.2 Looking Forward -- Chapter 2 Bibliometric Analyses of the Network Clustering Literature -- 2.1 Introduction -- 2.2 Data Collection and Cleaning -- 2.2.1 Most Cited/Citing Works -- 2.2.2 The Boundary Problem for Citation Networks -- 2.3 Analyses of the Citation Networks -- 2.3.1 Components -- 2.3.2 The CPM Path of the Main Citation Network -- 2.3.3 Key‐Route Paths -- 2.3.4 Positioning Sets of Selected Works in a Citation Network -- 2.4 Link Islands in the Clustering Network Literature -- 2.4.1 Island 10: Community Detection and Blockmodeling -- 2.4.2 Island 7: Engineering Geology -- 2.4.3 Island 9: Geophysics -- 2.4.4 Island 2: Electromagnetic Fields and their Impact on Humans -- 2.4.5 Limitations and Extensions -- 2.5 Authors -- 2.5.1 Productivity Inside Research Groups -- 2.5.2 Collaboration -- 2.5.3 Citations Among Authors Contributing to the Network Partitioning Literature -- 2.5.4 Citations Among Journals -- 2.5.5 Bibliographic Coupling -- 2.5.6 Linking Through a Jaccard Network -- 2.6 Summary and Future Work -- Acknowledgements -- References -- Chapter 3 Clustering Approaches to Networks -- 3.1 Introduction -- 3.2 Clustering -- 3.2.1 The Clustering Problem -- 3.2.2 Criterion Functions -- 3.2.3 Cluster‐Error Function/Examples -- 3.2.4 The Complexity of the Clustering Problem -- 3.3 Approaches to Clustering -- 3.3.1 Local Optimization -- 3.3.2 Dynamic Programming -- 3.3.3 Hierarchical Methods -- 3.3.4 Adding Hierarchical Methods -- 3.3.5 The Leaders Method -- 3.4 Clustering Graphs and Networks -- 3.5 Clustering in Graphs and Networks -- 3.5.1 An Indirect Approach -- 3.5.2 A Direct Approach: Blockmodeling -- 3.5.3 Graph Theoretic Approaches -- 3.6 Agglomerative Method for Relational Constraints
  • 8.3.2 Weak Structural Balance -- 8.3.3 Blockmodeling -- 8.3.4 Community Detection -- 8.4 Empirical Analysis -- Summary and Future Work -- References -- Chapter 9 Partitioning Multimode Networks -- 9.1 Introduction -- 9.2 Two‐Mode Partitioning -- 9.3 Community Detection -- 9.4 Dual Projection -- 9.5 Signed Two‐Mode Networks -- 9.6 Spectral Methods -- 9.7 Clustering -- 9.8 More Complex Data -- 9.9 Conclusion -- References -- Chapter 10 Blockmodeling Linked Networks -- 10.1 Introduction -- 10.2 Blockmodeling Linked Networks -- 10.2.1 Separate Analysis -- 10.2.2 A True Linked Blockmodeling Approach -- 10.2.3 Weighting of Different Parts of a Linked Network -- 10.3 Examples -- 10.3.1 Co‐authorship Network at Two Time‐points -- 10.3.2 A Multilevel Network of Participants at a Trade Fair for TV Programs -- 10.4 Conclusion -- Acknowledgements -- References -- Chapter 11 Bayesian Stochastic Blockmodeling -- 11.1 Introduction -- 11.2 Structure Versus Randomness in Networks -- 11.3 The Stochastic Blockmodel -- 11.4 Bayesian Inference: The Posterior Probability of Partitions -- 11.5 Microcanonical Models and the Minimum Description Length Principle -- 11.6 The ``Resolution Limit'' Underfitting Problem and the Nested SBM -- 11.7 Model Variations -- 11.7.1 Model Selection -- 11.7.2 Degree Correction -- 11.7.3 Group Overlaps -- 11.7.4 Further Model Extensions -- 11.8 Efficient Inference Using Markov Chain Monte Carlo -- 11.9 To Sample or To Optimize? -- 11.10 Generalization and Prediction -- 11.11 Fundamental Limits of Inference: The Detectability-Indetectability Phase Transition -- 11.12 Conclusion -- References -- Chapter 12 Structured Networks and Coarse‐Grained Descriptions: A Dynamical Perspective -- 12.1 Introduction -- 12.2 Part I: Dynamics on and of Networks -- 12.2.1 General Setup -- 12.2.2 Consensus Dynamics -- 12.2.3 Diffusion Processes and Random Walks
  • 12.3 Part II: The Influence of Graph Structure on Network Dynamics -- 12.3.1 Time Scale Separation in Partitioned Networks -- 12.3.2 Strictly Invariant Subspaces of the Network Dynamics and External Equitable Partitions -- 12.3.3 Structural Balance: Consensus on Signed Networks and Polarized Opinion Dynamics -- 12.4 Part III: Using Dynamical Processes to Reveal Network Structure -- 12.4.1 A Generic Algorithmic Framework for Dynamics‐Based Network Partitioning and Coarse Graining -- 12.4.2 Extending the Framework by using other Measures -- 12.5 Discussion -- Acknowledgements -- References -- Chapter 13 Scientific Co‐Authorship Networks -- 13.1 Introduction -- 13.2 Methods -- 13.2.1 Blockmodeling -- 13.2.2 Measuring the Obtained Blockmodels' Stability -- 13.3 The Data -- 13.4 The Structure of Obtained Blockmodels -- 13.5 Stability of the Obtained Blockmodel Structures -- 13.5.1 Clustering of Scientific Disciplines According to Different Operationalizations of Core Stability -- 13.5.2 Explaining the Stability of Cores -- 13.6 Conclusions -- Acknowledgements -- References -- Chapter 14 Conclusions and Directions for Future Work -- 14.1 Issues Raised within Chapters -- 14.2 Linking Ideas Found in Different Chapters -- 14.3 A Brief Summary and Conclusion -- References -- Topic Index -- Person Index -- EULA
  • 6.4.4 Regular Equivalence: The REGE Algorithms -- 6.4.5 Indirect Approaches: Finding Clusters, Interpreting Blocks -- 6.5 Direct Approaches -- 6.5.1 Generalized Blockmodeling -- 6.5.2 Generalized Blockmodeling of Valued Networks -- 6.5.3 Deviational Generalized Blockmodeling -- 6.6 On the Selection of Suitable Approaches -- 6.7 Examples -- 6.7.1 EIES Friendship Data at Time 2 -- 6.7.2 Commodity Trade Within EU/EFTA 2010 -- 6.8 Conclusion -- Acknowledgements -- References -- Chapter 7 Treating Missing Network Data Before Partitioning -- 7.1 Introduction -- 7.2 Types of Missing Network Data -- 7.2.1 Measurement Errors in Recorded (Or Reported) Ties -- 7.2.2 Item Non‐Response -- 7.2.3 Actor Non‐Response -- 7.3 Treatments of Missing Data (Due to Actor Non‐Response) -- 7.3.1 Reconstruction -- 7.3.2 Imputations of the Mean Values of Incoming Ties -- 7.3.3 Imputations of the Modal Values of Incoming Ties -- 7.3.4 Reconstruction and Imputations Based on Modal Values of Incoming Ties -- 7.3.5 Imputations of the Total Mean -- 7.3.6 Imputations of Median of the Three Nearest Neighbors based on Incoming Ties -- 7.3.7 Null Tie Imputations -- 7.3.8 Blockmodel Results for the Whole and Treated Networks -- 7.4 A Study Design Examining the Impact of Non‐Response Treatments on Clustering Results -- 7.4.1 Some Features of Indirect and Direct Blockmodeling -- 7.4.2 Design of the Simulation Study -- 7.4.3 The Real Networks Used in the Simulation Studies -- 7.5 Results -- 7.5.1 Indirect Blockmodeling of Real Valued Networks -- 7.5.2 Indirect Blockmodeling on Real Binary Networks -- 7.5.3 Direct Blockmodeling of Binary Real Networks -- 7.6 Conclusions -- Acknowledgements -- References -- Chapter 8 Partitioning Signed Networks -- 8.1 Notation -- 8.2 Structural Balance Theory -- 8.2.1 Weak Structural Balance -- 8.3 Partitioning -- 8.3.1 Strong Structural Balance