Unfortunately, we dropped the support for PageRank. For performance
reasons, our implementation assumed that the pageRank vector fits into
memory, making it unsuitable for very large graphs.

I'd recommend you have a look at Apache Giraph, a framework dedicated to
large scale graph processing.


On 03.08.2012 10:27, Yan Liu (JIRA) wrote:
> Yan Liu created MAHOUT-1049:
> -------------------------------
> 
>              Summary: out of memory error when running PageRank
>                  Key: MAHOUT-1049
>                  URL: https://issues.apache.org/jira/browse/MAHOUT-1049
>              Project: Mahout
>           Issue Type: Improvement
>             Reporter: Yan Liu
> 
> 
> We always met a 'out of memory' error when running PageRank. Since we have to 
> run large-scale data, is there any way for improvement?
> 
> --
> This message is automatically generated by JIRA.
> If you think it was sent incorrectly, please contact your JIRA 
> administrators: 
> https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
> For more information on JIRA, see: http://www.atlassian.com/software/jira
> 
>         
> 

Reply via email to