I have experimented with this, but never used it in anger. The method I used was simply to add the target variable while clustering. Results were interesting.
A much more interesting approach is detailed here: http://www.cs.cmu.edu/~epxing/papers/Old_papers/xing_nips02_metric.pdf This also looks interesting: http://www.slideshare.net/zukun/metric-learning-icml2010-tutorial On Sun, Jul 14, 2013 at 1:30 PM, Martin Arrowsmith < [email protected]> wrote: > Hello Mahout Experts! > > I just started using Mahout, and I was wondering if there was an example or > tutorial of using Mahout for semi-supervised learning. I have a few labeled > data, and a bunch of unlabeled data. I'd like to try to create a larger > training set than the labeled data by performing a semi-supervised learning > technique. > > Does anyone know if Mahout has been used to do this ? > > Thank you for any insight you can give! > > Best wishes, > > Martin >
