Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Hierarchical clustering of networks
open-in-new
<p><a href="/facts/Hierarchical_clustering/KxXs6GPK">Hierarchical clustering</a> is one method for finding <a href="/facts/Community_structure/CKfUKFYh">community structures</a> in a <a href="/facts/Graph_(discrete_mathematics)/kw3eIBUe">network</a>. The technique arranges the network into a hierarchy of groups according to a specified weight function. The data can then be represented in a tree structure known as a <a href="/facts/Dendrogram/FI8EMSEv">dendrogram</a>. Hierarchical clustering can either be <a href="/facts/Agglomerative_clustering/HUeDnWPt">agglomerative</a> or <a href="/facts/Divisive_clustering/KxXs6GPK">divisive</a> depending on whether one proceeds through the algorithm by adding links to or removing links from the network, respectively. One divisive technique is the <a href="/facts/Girvan%E2%80%93Newman_algorithm/zo2fvBST">Girvan–Newman algorithm</a>. </p>