Learn on Source, Refine on Target:A Model Transfer Learning Framework with Random Forests

TL;DR

This paper introduces two novel transfer learning algorithms for decision forests that adapt models from a source to a target domain, demonstrating significant experimental improvements.

Contribution

It presents two new random forest transfer algorithms—structure modification and parameter tuning—and their ensemble, advancing transfer learning techniques for decision forests.

Findings

Algorithms outperform baseline methods in experiments

Ensemble of both methods yields better results

Effective adaptation from source to target domain

Abstract

We propose novel model transfer-learning methods that refine a decision forest model M learned within a "source" domain using a training set sampled from a "target" domain, assumed to be a variation of the source. We present two random forest transfer algorithms. The first algorithm searches greedily for locally optimal modifications of each tree structure by trying to locally expand or reduce the tree around individual nodes. The second algorithm does not modify structure, but only the parameter (thresholds) associated with decision nodes. We also propose to combine both methods by considering an ensemble that contains the union of the two forests. The proposed methods exhibit impressive experimental results over a range of problems.