You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@flink.apache.org by "Josep Rubió (JIRA)" <ji...@apache.org> on 2016/02/17 22:27:18 UTC

[jira] [Commented] (FLINK-1707) Add an Affinity Propagation Library Method

    [ https://issues.apache.org/jira/browse/FLINK-1707?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15151223#comment-15151223 ] 

Josep Rubió commented on FLINK-1707:
------------------------------------

Hi Vasia,

I've been working with the binary variable model of Affinity Propagation (https://www.psi.toronto.edu/pubs2/2009/NC09%20-%20SimpleAP.pdf). What I can tell about it (knowing almost nothing about bayesian networks and distributed computing) is that this model is easier to extend than the original one when adding new constraints. 

I've been doing some tests comparing the results of both papers and although they have different intermediate results (due to the scheduling of the calculations) they seem to produce same clusters.

Said this, I don't know if you are interested in the implementation of this one or the original one.

> Add an Affinity Propagation Library Method
> ------------------------------------------
>
>                 Key: FLINK-1707
>                 URL: https://issues.apache.org/jira/browse/FLINK-1707
>             Project: Flink
>          Issue Type: New Feature
>          Components: Gelly
>            Reporter: Vasia Kalavri
>            Priority: Minor
>
> This issue proposes adding the an implementation of the Affinity Propagation algorithm as a Gelly library method and a corresponding example.
> The algorithm is described in paper [1] and a description of a vertex-centric implementation can be found is [2].
> [1]: http://www.psi.toronto.edu/affinitypropagation/FreyDueckScience07.pdf
> [2]: http://event.cwi.nl/grades2014/00-ching-slides.pdf



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)