Distribution-Based Categorization of Classifier Transfer Learning

TL;DR

This paper reviews classification transfer learning methods and introduces a distribution-based categorization with standardized terminology to clarify the field and facilitate better understanding and application.

Contribution

It provides a comprehensive review and proposes a novel distribution-based categorization framework with standardized nomenclature for classification transfer learning methods.

Findings

Three main TL categories are identified and discussed.

A common nomenclature for classification TL methods is proposed.

The categorization is illustrated with examples.

Abstract

Transfer Learning (TL) aims to transfer knowledge acquired in one problem, the source problem, onto another problem, the target problem, dispensing with the bottom-up construction of the target model. Due to its relevance, TL has gained significant interest in the Machine Learning community since it paves the way to devise intelligent learning models that can easily be tailored to many different applications. As it is natural in a fast evolving area, a wide variety of TL methods, settings and nomenclature have been proposed so far. However, a wide range of works have been reporting different names for the same concepts. This concept and terminology mixture contribute however to obscure the TL field, hindering its proper consideration. In this paper we present a review of the literature on the majority of classification TL methods, and also a distribution-based categorization of TL with a common nomenclature suitable to classification problems. Under this perspective three main TL categories are presented, discussed and illustrated with examples.