In the last decades, the analysis of complex networks has received increasing attention from several, heterogeneous fields of research. One of the hottest topics in network science is Community Discovery (henceforth CD), the task of clustering network entities belonging to topological dense regions of a graph. Although many methods and algorithms have been proposed to cope with this problem, and related issues such as their evaluation and comparison, few of them are integrated into a common software framework, making hard and time-consuming to use, study and compare them. Only a handful of the most famous methods are available in generic libraries such as NetworkX and Igraph. To cope with this issue, we introduce a novel library designed to easily select/apply community discovery methods on network datasets, evaluate/compare the obtained clustering and visualize the results.
CDlib: A python library to extract, compare and evaluate communities from complex networks
Rossetti G;Milli L;
2020
Abstract
In the last decades, the analysis of complex networks has received increasing attention from several, heterogeneous fields of research. One of the hottest topics in network science is Community Discovery (henceforth CD), the task of clustering network entities belonging to topological dense regions of a graph. Although many methods and algorithms have been proposed to cope with this problem, and related issues such as their evaluation and comparison, few of them are integrated into a common software framework, making hard and time-consuming to use, study and compare them. Only a handful of the most famous methods are available in generic libraries such as NetworkX and Igraph. To cope with this issue, we introduce a novel library designed to easily select/apply community discovery methods on network datasets, evaluate/compare the obtained clustering and visualize the results.File | Dimensione | Formato | |
---|---|---|---|
prod_439448-doc_157650.pdf
accesso aperto
Descrizione: CDlib: A python library to extract, compare and evaluate communities from complex networks
Tipologia:
Versione Editoriale (PDF)
Dimensione
256.89 kB
Formato
Adobe PDF
|
256.89 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.