I'm curious as to whether research been done into random forests that combine unsupervised with supervised learning in a way allowing a single algorithm to find patterns in, and work with, multiple different data sets. I have googled every possible way to find research on this, and have come up empty. Can anyone point me in the right direction?
The combination of unsupervised learning and supervised learning is referred to as
semi-supervised learning, which is the concept that I believe you are searching for.
Label propagation is often cited when outlining the heuristics of
semi-supervised learning. The essence is to employ clustering, but to use a tiny set of known cases in order to derive (or propogate) the labels of the clusters. Hence one is able to use a small set of labeled cases to classify a much larger set of unsupervised data.
Here are some references:
- Wikipedia has an entry on the
- The scikit learn User Guide is often a useful starting point and has a label propogation routine.
- There are, in fact, papers treating
- Another one here
Hope this helps!