Spectral density-based clustering algorithms for complex networks

Frontiers in Neuroscience

Neuroscience

Janaina Mourão-Miranda¹  André Fujita²  Taiane Coelho Ramos³ 

[1] Department of Computer Science, Centre for Medical Image Computing, University College London, London, United Kingdom;Max Planck Centre for Computational Psychiatry and Ageing Research, University College London, London, United Kingdom;Department of Computer Science, Institute of Mathematics and Statistics, University of São Paulo, São Paulo, Brazil;Department of Computer Science, Institute of Mathematics and Statistics, University of São Paulo, São Paulo, Brazil;Department of Computer Science, Centre for Medical Image Computing, University College London, London, United Kingdom;

关键词: clustering;    graphs and networks;    graph theory;    spectral methods;    electrocorticography;    complex networks;   

DOI  :  10.3389/fnins.2023.926321

 received in 2022-04-22, accepted in 2023-03-10,  发布年份 2023

来源: Frontiers

【 摘 要 】

IntroductionClustering is usually the first exploratory analysis step in empirical data. When the data set comprises graphs, the most common approaches focus on clustering its vertices. In this work, we are interested in grouping networks with similar connectivity structures together instead of grouping vertices of the graph. We could apply this approach to functional brain networks (FBNs) for identifying subgroups of people presenting similar functional connectivity, such as studying a mental disorder. The main problem is that real-world networks present natural fluctuations, which we should consider.MethodsIn this context, spectral density is an exciting feature because graphs generated by different models present distinct spectral densities, thus presenting different connectivity structures. We introduce two clustering methods: k-means for graphs of the same size and gCEM, a model-based approach for graphs of different sizes. We evaluated their performance in toy models. Finally, we applied them to FBNs of monkeys under anesthesia and a dataset of chemical compounds.ResultsWe show that our methods work well in both toy models and real-world data. They present good results for clustering graphs presenting different connectivity structures even when they present the same number of edges, vertices, and degree of centrality.DiscussionWe recommend using k-means-based clustering for graphs when graphs present the same number of vertices and the gCEM method when graphs present a different number of vertices.

【 授权许可】

Unknown   
Copyright © 2023 Ramos, Mourão-Miranda and Fujita.