Decision Trees for Instance Transfer

Instance-transfer learning has emerged as a promising learning framework to boost performance of predictive models for a target domain by exploiting data from source domains. The success of the framework depends on the relevance of the source data to the target data. This paper proposes a decision-tree approach for instance transfer when the source and target data are relevant with respect to a strict subset of input features. Experimental results on real-world data sets demonstrate that the proposed approach outperforms existing instance-transfer approaches when the source and target data are partially related.