More Like this

1. MLN-Subdue: Substructure Discovery In Homogeneous Multilayer Networks [MLN-Subdue: Substructure Discovery In Homogeneous Multilayer Networks]

   https://doi.org/10.5220/0012906200003838  

   Rai, Anish; Roy, Anamitra; Santra, Abhishek; Chakravarthy, Sharma (January 2024, SCITEPRESS - Science and Technology Publications)
2. Degree centrality and root finding in growing random networks

   https://doi.org/10.1214/23-EJP930  

   Banerjee, Sayan; Huang, Xiangying (January 2023, Electronic Journal of Probability)
3. Centrality measures in networks

   https://doi.org/10.1007/s00355-023-01456-4  

   Bloch, Francis; Jackson, Matthew O.; Tebaldi, Pietro (April 2023, Social Choice and Welfare)
4. Centrality in dynamic competition networks

   https://doi.org/10.1007/978-3-030-36683-4_9  

   Bonato, Anthony; Eikmeier, Nicole; Gleich, David F.; Malik, Rehan (December 2019, Complex Networks and Their Applications VIII)
5. Rapid Betweenness Centrality Estimates for Transportation Networks using Capsule Networks

   https://doi.org/10.1109/TransAI54797.2022.00023  

   Matin, Abdul; Armstrong, Samuel; Mitra, Saptashwa; Pallickara, Shrideep; Pallickara, Sangmi Lee (September 2022, 2022 Fourth International Conference on Transdisciplinary AI (TransAI))

   Measuring importance of nodes in a graph is one of the key aspects in graph analysis. Betweenness centrality (BC) measures the amount of influence that a node has over the flow of information in a graph. However, the computation complexity of calculating BC is extremely high with large-scale graphs. This is especially true when analyzing the road networks with millions of nodes and edges. In this study, we propose a deep learning architecture RoadCaps to estimate BC with sub-second latencies. RoadCaps aggregates features from neighbor nodes using Graph Convolutional Networks and estimates the node level BC by mapping low-level concept to high-level information using Capsule Networks. Our empirical benchmarks demonstrates that RoadCaps outperforms base models such as GCN and GCNFCL in both accuracy and robustness. On average, RoadCaps generates a node’s BC value in 7.5 milliseconds. 

   more » « less