Difference between fuzzy model averaging and overlapping?
When you sample from the posterior and take the vertex marginals, is it proper to say that we can interpret the marginals for a given vertex as being the degree of membership in the communities (fuzzy community membership)? If so, how does this differ from the overlapping blockstate? I saw in the mailing list that overlapping is only supported at the base level: http://main-discussion-list-for-the-graph-tool-project.982480.n3.nabble.com/... But, even if it were supported at every level, what does this achieve that the fuzzy model averaging doesn't? Could you do model averaging with the overlapping state too? E.g., in sample 1 vertex A is in communities c1, c2. In sample 2 vertex A is in communities c1, c4. Etc. Would this be in some way a more accurate measure of multiple community membership than the fuzzy? Thanks
Am 17.02.20 um 18:35 schrieb Deklan Webster:
When you sample from the posterior and take the vertex marginals, is it proper to say that we can interpret the marginals for a given vertex as being the degree of membership in the communities (fuzzy community membership)?
It can be interpreted as the posterior probability of a node belonging to a particular group.
If so, how does this differ from the overlapping blockstate?
It's different, because the generative model is not the same. In an overlapping SBM the nodes can belong to multiple groups at the same time. In the non-overlapping version, this is not possible. The marginal distribution just conveys the uncertainty of the inference, not joint membership. Best, Tiago -- Tiago de Paula Peixoto <tiago@skewed.de>
Thanks for fast reply. "The marginal distribution just conveys the uncertainty of the inference, not joint membership." Is it not the case that those nodes who would be members of multiple communities (in the overlapping model) would also appear in those communities during different samples of the posterior? On Mon, Feb 17, 2020 at 12:35 PM Deklan Webster <deklanw@gmail.com> wrote:
When you sample from the posterior and take the vertex marginals, is it proper to say that we can interpret the marginals for a given vertex as being the degree of membership in the communities (fuzzy community membership)?
If so, how does this differ from the overlapping blockstate? I saw in the mailing list that overlapping is only supported at the base level:
http://main-discussion-list-for-the-graph-tool-project.982480.n3.nabble.com/...
But, even if it were supported at every level, what does this achieve that the fuzzy model averaging doesn't? Could you do model averaging with the overlapping state too? E.g., in sample 1 vertex A is in communities c1, c2. In sample 2 vertex A is in communities c1, c4. Etc. Would this be in some way a more accurate measure of multiple community membership than the fuzzy?
Thanks
participants (2)
-
Deklan Webster -
Tiago de Paula Peixoto