Heterogeneous Transfer Learning via Deep Matrix Completion with Adversarial Kernel Embedding

Authors

  • Haoliang Li Nanyang Technological University
  • Sinno Jialin Pan Nanyang Technological University
  • Renjie Wan Nanyang Technological University
  • Alex C. Kot Nanyang Technological University

DOI:

https://doi.org/10.1609/aaai.v33i01.33018602

Abstract

Heterogeneous Transfer Learning (HTL) aims to solve transfer learning problems where a source domain and a target domain are of heterogeneous types of features. Most existing HTL approaches either explicitly learn feature mappings between the heterogeneous domains or implicitly reconstruct heterogeneous cross-domain features based on matrix completion techniques. In this paper, we propose a new HTL method based on a deep matrix completion framework, where kernel embedding of distributions is trained in an adversarial manner for learning heterogeneous features across domains. We conduct extensive experiments on two different vision tasks to demonstrate the effectiveness of our proposed method compared with a number of baseline methods.

Downloads

Published

2019-07-17

How to Cite

Li, H., Pan, S. J., Wan, R., & Kot, A. C. (2019). Heterogeneous Transfer Learning via Deep Matrix Completion with Adversarial Kernel Embedding. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8602-8609. https://doi.org/10.1609/aaai.v33i01.33018602

Issue

Section

AAAI Technical Track: Vision