[
https://issues.apache.org/jira/browse/MAHOUT-1214?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13665190#comment-13665190
]
Shannon Quinn commented on MAHOUT-1214:
---------------------------------------
This all looks great. With the work I did on Eigencuts this semester, there are
some optimizations in the data structures I'd like to test that might further
help spectral kmeans' performance, in addition to looking into ball kmeans,
streaming kmeans, and SSVD.
I still have a question to Yiqun: if you've implemented an orthogonality check
in EigenVerificationJob, how is this not something that can be applied to
EigenVerificationJob in general, as opposed to only spectral kmeans?
> Improve the accuracy of the Spectral KMeans Method
> --------------------------------------------------
>
> Key: MAHOUT-1214
> URL: https://issues.apache.org/jira/browse/MAHOUT-1214
> Project: Mahout
> Issue Type: Improvement
> Components: Clustering
> Affects Versions: 0.7
> Environment: Mahout 0.7
> Reporter: Yiqun Hu
> Labels: clustering, improvement
>
> The current implementation of the spectral KMeans algorithm (Andrew Ng. etc.
> NIPS 2002) in version 0.7 has two serious issues. These two incorrect
> implementations make it fail even for a very obvious trivial dataset. We have
> implemented a solution to resolve these two issues and hope to contribute
> back to the community.
> # Issue 1:
> The EigenVerificationJob in version 0.7 does not check the orthogonality of
> eigenvectors, which is necessary to obtain the correct clustering results for
> the case of K>1; We have an idea and implementation to select based on
> cosAngle/orthogonality;
> # Issue 2:
> The random seed initialization of KMeans algorithm is not optimal and
> sometimes a bad initialization will generate wrong clustering result. In this
> case, the selected K eigenvector actually provides a better way to initalize
> cluster centroids because each selected eigenvector is a relaxed indicator of
> the memberships of one cluster. For every selected eigenvector, we use the
> data point whose eigen component achieves the maximum absolute value.
> We have already verified our improvement on synthetic dataset and it shows
> that the improved version get the optimal clustering result while the current
> 0.7 version obtains the wrong result.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
