After reading the wiki page for biclustering (https://en.m.wikipedia.org/wiki/Biclustering), I am really confused on what is the difference between biclustering and clustering?
Any explanation/comparisons would be really appreciated. Many thanks.
$\begingroup$
$\endgroup$
Add a comment
|
$\begingroup$
$\endgroup$
Clustering find groups of observations in a p dimensional space (p features).
Biclustering enables you to find clusters in a subset of features. Then why would you need other features than this subset to perform the clustering? Because locally you may find dimensions a & b useful to identify a cluster (green cluster in the figure) and somewhere else in the space, dimensions b & c might be useful to identify other clusters (light blue and purple clusters on the figure).
Sources :
