Showing results for 
Search instead for 
Did you mean: 

Head's Up! Site maintenance this Wednesday, February 1. Disruptions expected as we migrate the forums.

Community detection for bipartite graph


Is there a way to detect communities in a bipartite graph? 

For bipartite graphs (e.g. users and movies), I know it is possible to calculate similarities for pairs of nodes (i.e. users). What I would like to do is to get the groups of users that all together have at least 80% similarity (based on the number of common movies). 

I also saw that an alternative way would be to convert this to a monopartite graph of relationships between users with the number of common movies as weight, but then we would lose the information of what are the common movies. Then, for example, there could be a group where each pair of users has at least 80% similarity but the similarity between the whole group and a specific user in the group could be less than 80%. 

Is there any way to solve this?