Spectral cyclicality of networks
Abstract
We introduce the spectral influence and spectral cyclicality based on the largest eigenvalue of a graph adjacency matrix, two novel concepts of centrality capturing diffusion and interdependence from a local and a global point of view respectively. We define a new clustering algorithm to distinguish communities with high cyclicality and interdependence, allowing overlapping, and we conclude our study with an application to the input-output analysis in the case of the Moroccan economy.
- Publication:
-
arXiv e-prints
- Pub Date:
- May 2023
- DOI:
- 10.48550/arXiv.2305.02371
- arXiv:
- arXiv:2305.02371
- Bibcode:
- 2023arXiv230502371R
- Keywords:
-
- Computer Science - Social and Information Networks;
- Mathematics - Combinatorics;
- 05C22;
- 05C38;
- 05C85;
- 05C90