A survey of transfer learning

TLDR

Machine learning assumes training and testing data come from the same domain, but in many real‑world scenarios this assumption fails and training data can be scarce, motivating the need for transfer learning. This survey aims to formally define transfer learning, review current solutions and applications, and address the need for high‑performance learners using data from different domains. The paper surveys existing transfer learning methods, provides software download links, and discusses future research directions. The surveyed transfer learning solutions are data‑size independent and suitable for big‑data environments.

Abstract

Machine learning and data mining techniques have been used in numerous real-world applications. An assumption of traditional machine learning methodologies is the training data and testing data are taken from the same domain, such that the input feature space and data distribution characteristics are the same. However, in some real-world machine learning scenarios, this assumption does not hold. There are cases where training data is expensive or difficult to collect. Therefore, there is a need to create high-performance learners trained with more easily obtained data from different domains. This methodology is referred to as transfer learning. This survey paper formally defines transfer learning, presents information on current solutions, and reviews applications applied to transfer learning. Lastly, there is information listed on software downloads for various transfer learning solutions and a discussion of possible future research work. The transfer learning solutions surveyed are independent of data size and can be applied to big data environments.