Distant Domain Transfer Learning

Authors

  • Ben Tan Hong Kong University of Science and Technology
  • Yu Zhang Hong Kong University of Science and Technology
  • Sinno Pan Nanyang Technological University
  • Qiang Yang Hong Kong University of Science and Technology

DOI:

https://doi.org/10.1609/aaai.v31i1.10826

Keywords:

transfer learning, distant domain, deep learning

Abstract

In this paper, we study a novel transfer learning problem termed Distant Domain Transfer Learning (DDTL). Different from existing transfer learning problems which assume that there is a close relation between the source domain and the target domain, in the DDTL problem, the target domain can be totally different from the source domain. For example, the source domain classifies face images but the target domain distinguishes plane images. Inspired by the cognitive processof human where two seemingly unrelated concepts can be connected by learning intermediate concepts gradually, we propose a Selective Learning Algorithm (SLA) to solve the DDTL problem with supervised autoencoder or supervised convolutional autoencoder as a base model for handling different types of inputs. Intuitively, the SLA algorithm selects usefully unlabeled data gradually from intermediate domains as a bridge to break the large distribution gap for transferring knowledge between two distant domains. Empirical studies on image classification problems demonstrate the effectiveness of the proposed algorithm, and on some tasks the improvement in terms of the classification accuracy is up to 17% over “non-transfer” methods.

Downloads

Published

2017-02-13

How to Cite

Tan, B., Zhang, Y., Pan, S., & Yang, Q. (2017). Distant Domain Transfer Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.10826