• Home
  • Search
  • Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation
  • Cite Icon131
  • https://doi.org/10.24963/ijcai.2018/412Copy DOI Icon

Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation

  • Jul 1, 2018
  • Yuguang Yan +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Heterogeneous domain adaptation (HDA) aims to exploit knowledge from a heterogeneous source domain to improve the learning performance in a target domain. Since the feature spaces of the source and target domains are different, the transferring of knowledge is extremely difficult. In this paper, we propose a novel semi-supervised algorithm for HDA by exploiting the theory of optimal transport (OT), a powerful tool originally designed for aligning two different distributions. To match the samples between heterogeneous domains, we propose to preserve the semantic consistency between heterogeneous domains by incorporating label information into the entropic Gromov-Wasserstein discrepancy, which is a metric in OT for different metric spaces, resulting in a new semi-supervised scheme. Via the new scheme, the target and transported source samples with the same label are enforced to follow similar distributions. Lastly, based on the Kullback-Leibler metric, we develop an efficient algorithm to optimize the resultant problem. Comprehensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of our proposed method.

Similar Papers
  • Research Article
  • Citations157

Heterogeneous Domain Adaptation: An Unsupervised Approach.

  • Nov 30, 2020
  • IEEE Transactions on Neural Networks and Learning Systems
  • Feng Liu +2
  • Research Article
  • Citations77

Unsupervised Heterogeneous Domain Adaptation via Shared Fuzzy Equivalence Relations

  • Dec 01, 2018
  • IEEE Transactions on Fuzzy Systems
  • Feng Liu +2
  • Research Article
  • Citations61

Cross-domain structure preserving projection for heterogeneous domain adaptation

  • Oct 09, 2021
  • Pattern Recognition
  • Qian Wang +1
  • Research Article
  • Citations16

Heterogeneous Domain Adaptation With Adversarial Neural Representation Learning: Experiments on E-Commerce and Cybersecurity.

  • Feb 01, 2023
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Mohammadreza Ebrahimi +3
  • Research Article
  • Citations48

Heterogeneous Domain Adaptation via Nonlinear Matrix Factorization.

  • May 29, 2019
  • IEEE Transactions on Neural Networks and Learning Systems
  • Haoliang Li +3
  • Conference Article
  • Citations5

Deep Domain Adaptation based Cloud Type Detection using Active and Passive Satellite Data

  • Dec 10, 2020
  • Xin Huang +6
  • Research Article
  • Citations42

Multisource Heterogeneous Domain Adaptation With Conditional Weighting Adversarial Network.

  • Apr 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Yuan Yao +3
  • Conference Article
  • Citations1

Adaptive Teacher-and-Student Model for Heterogeneous Domain Adaptation

  • Nov 01, 2019
  • Yunyun Wang +3
  • Conference Article
  • Citations5

Heterogeneous domain adaptation using previously learned classifier for object detection problem

  • Oct 01, 2014
  • Azadeh Sadat Mozafari +1
  • Research Article
  • Citations32

Heterogeneous Multidomain Recommender System Through Adversarial Learning.

  • Nov 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Wenhui Liao +4
  • Research Article
  • Citations29

A New Belief-Based Bidirectional Transfer Classification Method.

  • Aug 01, 2022
  • IEEE Transactions on Cybernetics
  • Zhun-Ga Liu +4
  • Research Article
  • Citations2

Heterogeneous domain adaptation by Features Normalization and Data Topology Preserving

  • Jul 29, 2022
  • Knowledge-Based Systems
  • Mohammad Amin Pirbonyeh +3
  • Conference Article
  • Citations11

Heterogeneous unsupervised domain adaptation based on fuzzy feature fusion

  • Jul 01, 2017
  • Feng Liu +2
  • Conference Article
  • Citations1

Incremental Discriminant Learning for Heterogeneous Domain Adaptation

  • Nov 01, 2015
  • Peng Han +1
  • Research Article
  • Citations5

Robust multiple subspaces transfer for heterogeneous domain adaptation

  • Apr 04, 2024
  • Pattern Recognition
  • Youfa Liu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.