getNMI(A,B)
call:
NMI = getNMI(A,B)
This function computes the Normalized Mutual Information (NMI) between
2 modular partitions or community structures given in vectors A and B.
NMI is a measure of the similarity between the two graph partitions, and
its interpretation follows that of canonical Mutual Information, i.e.
assuming that I have complete knowledge of partition A, how much knowledge
can I get, from A, about partition B? If A and B are identical, then
NMI = 1, whereas if A and B are independent, NMI --> 0.
INPUT
A : Community partition of graph A *
B : Community partition of graph B *
* A and B are N-length vectors, where each i-th element is the integer
labeling the k-th community to which node i-th was assigned.
OUTPUT
NMI : Normalized Mutual Information
References:
[1] Kuncheva & Hadjitodorov, 2004, IEEE Intern. Conf. on Syst. Man and Cybern.
[2] Alexander-Bloch et al., 2012, NeuroImage
引用
Ruggero G. Bettinardi (2024). getNMI(A,B) (https://www.mathworks.com/matlabcentral/fileexchange/62974-getnmi-a-b), MATLAB Central File Exchange. 取得済み .
MATLAB リリースの互換性
プラットフォームの互換性
Windows macOS Linuxカテゴリ
タグ
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!バージョン | 公開済み | リリース ノート | |
---|---|---|---|
1.0.0.0 |