Locality-constrained transfer coding for heterogeneous domain adaptation

Jingjing Li, Ke Lu, Lei Zhu, Zhihui Li

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

10 Citations (Scopus)


Currently, most of widely used databases are label-wise. In other words, people organize their data with corresponding labels, e.g., class information, keywords and description, for the convenience of indexing and retrieving. However, labels of the data from a novel application usually are not available, and labeling by hand is very expensive. To address this, we propose a novel approach based on transfer learning. Specifically, we aim at tackling heterogeneous domain adaptation (HDA). HDA is a crucial topic in transfer learning. Two inevitable issues, feature discrepancy and distribution divergence, get in the way of HDA. However, due to the significant challenges of HDA, previous work commonly focus on handling one of them and neglect the other. Here we propose to deploy locality-constrained transfer coding (LCTC) to simultaneously alleviate the feature discrepancy and mitigate the distribution divergence. Our method is powered by two tactics: feature alignment and distribution alignment. The former learns new transferable feature representations by sharing-dictionary coding and the latter aligns the distribution gaps on the new feature space. By formulating the problem into a unified objective and optimizing it via an iterative fashion, the two tactics are reinforced by each other and the two domains are drawn closer under the new representations. Extensive experiments on image classification and text categorization verify the superiority of our method against several state-of-the-art approaches.

Original languageEnglish
Title of host publicationDatabases Theory and Applications
Subtitle of host publication28th Australasian Database Conference, ADC 2017 Brisbane, QLD, Australia, September 25–28, 2017 Proceedings
EditorsZi Huang, Xiaokui Xiao, Xin Cao
Place of PublicationCham Switzerland
Number of pages12
ISBN (Electronic)9783319681559
ISBN (Print)9783319681542
Publication statusPublished - 2017
Externally publishedYes
EventAustralasian Database Conference 2017 - Brisbane, Australia
Duration: 25 Sep 201728 Sep 2017
Conference number: 28th
https://link.springer.com/book/10.1007/978-3-319-68155-9 (Proceedings)

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceAustralasian Database Conference 2017
Abbreviated titleADC 2017
Internet address


  • Domain adaptation
  • Knowledge discovery
  • Transfer learning

Cite this