Centrality Measures in Networks Based on Nodes Attributes, Long-Range Interactions and Group Influence

Aleskerov, Fuad; Meshcheryakova, Natalia; Shvydun, Sergey

doi:10.2139/ssrn.3196962

Cited by 12 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There have also been attempts to integrate node/edge attributes with other graph structural measures. For instance, the degree and betweenness centralities are combined with node attributes in studying criminal networks [29]; nodes' attributes are used as a threshold in LRIC index [10]; and node/edge attributes are fused into graphlets [93,165]. We believe there is still great potential for developing novel structural approaches that integrate rich information on nodes and/or edges.…”

Section: Discussion and Outlookmentioning

confidence: 99%

A Network Science perspective of Graph Convolutional Networks: A survey

Jia¹,

Gabrys²,

Musiał³

2023

Preprint

View full text Add to dashboard Cite

The mining and exploitation of graph structural information have been the focal points in the study of complex networks. Traditional structural measures in Network Science focus on the analysis and modelling of complex networks from the perspective of network structure, such as the centrality measures, the clustering coefficient, and motifs and graphlets, and they have become basic tools for studying and understanding graphs. In comparison, graph neural networks, especially graph convolutional networks (GCNs), are particularly effective at integrating node features into graph structures via neighbourhood aggregation and message passing, and have been shown to significantly improve the performances in a variety of learning tasks. These two classes of methods are, however, typically treated separately with limited references to each other. In this work, aiming to establish relationships between them, we provide a network science perspective of GCNs. Our novel taxonomy classifies GCNs from three structural information angles, i.e., the layer-wise message aggregation scope, the message content, and the overall learning scope. Moreover, as a prerequisite for reviewing GCNs via a network science perspective, we also summarise traditional structural measures and propose a new taxonomy for them.Finally and most importantly, we draw connections between traditional structural approaches and graph convolutional networks, and discuss potential directions for future research.

show abstract

Section: Discussion and Outlookmentioning

confidence: 99%

A Network Science perspective of Graph Convolutional Networks: A survey

Jia¹,

Gabrys²,

Musiał³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…There have also been attempts to integrate node/edge attributes with other graph structural measures. For instance, the degree and betweenness centralities are combined with node attributes in studying criminal networks [162]; nodes' attributes are used as a threshold in LRIC index [163]; and node/edge attributes are fused into graphlets [164], [165]. We believe there is still great potential for developing novel structural approaches that integrate rich information on nodes and/or edges.…”

Section: F Discussion and Outlookmentioning

confidence: 99%

A Network Science Perspective of Graph Convolutional Networks: A Survey

2023

View full text Add to dashboard Cite

The mining and exploitation of graph structural information have been the focal points in the study of complex networks. Traditional structural measures in Network Science focus on the analysis and modelling of complex networks from the perspective of network structure, such as the centrality measures, the clustering coefficient, and motifs and graphlets, and they have become basic tools for studying and understanding graphs. In comparison, graph neural networks, especially graph convolutional networks (GCNs), are particularly effective at integrating node features into graph structures via neighbourhood aggregation and message passing, and have been shown to significantly improve the performances in a variety of learning tasks. These two classes of methods are, however, typically treated separately with limited references to each other. In this work, aiming to establish relationships between them, we provide a network science perspective of GCNs. Our novel taxonomy classifies GCNs from three structural information angles, i.e., the layer-wise message aggregation scope, the message content, and the overall learning scope. Moreover, as a prerequisite for reviewing GCNs via a network science perspective, we also summarise traditional structural measures and propose a new taxonomy for them. Finally and most importantly, we draw connections between traditional structural approaches and graph convolutional networks, and discuss potential directions for future research.

show abstract

“…Formulas of calculation of all above mentioned centrality measures that were derived from Aleskerov et al (2016) and Newman (2006) are provided in "Appendix Box 2". Also, Newman (2003) provides the profound overview of centrality measures in network graphs.…”

Section: Methodological Issuesmentioning

confidence: 99%

“…( 1) and ( 2) are measures for undirected network-graphs. Variations of degree measures for directed network-graphs are proposed in Aleskerov et al (2016).…”

Section: Implications and Conclusionmentioning

confidence: 99%

Unmanned aerial vehicles research in Scopus: an analysis and visualization of publication activity and research collaboration at the country level

Kotsemir

2019

Qual Quant

View full text Add to dashboard Cite

This article proposes a global bibliometric overview of unmanned aerial vehicle (UAVs) publications in the Scopus database during 1985-2015 at the country level. The article is structured as follows. The first section provides an introduction and overview of papers on the publication and patent activity in field of UAVs. Section two describes the methodological framework of the study. Section three provides an overview of co-publication activity in UAV research. Section four is devoted to an analysis of patterns of international collaboration in field of UAV research in Scopus. Finally, section five concludes the paper by summarizing the key findings from the analysis and illustrating the implications from the analysis and offering proposals for possible further developments in the field. This study uses a wide set of bibliometric indicators and network metrics for measuring different aspects of publication activity and citation levels as well as cross-country research collaboration on UAVs. In order to illustrate country-to-country research collaboration maps NodeXL software was applied.

show abstract

Centrality Measures in Networks Based on Nodes Attributes, Long-Range Interactions and Group Influence

Cited by 12 publications

References 0 publications

A Network Science perspective of Graph Convolutional Networks: A survey

A Network Science perspective of Graph Convolutional Networks: A survey

A Network Science Perspective of Graph Convolutional Networks: A Survey

Unmanned aerial vehicles research in Scopus: an analysis and visualization of publication activity and research collaboration at the country level

Contact Info

Product

Resources

About