• Home
  • Search
  • Transfer Learning with Dynamic Distribution Adaptation
  • Open Access IconOpen Access
  • Cite Icon287
  • https://doi.org/10.1145/3360309Copy DOI Icon

Transfer Learning with Dynamic Distribution Adaptation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Transfer learning aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions. However, in real applications, the marginal and conditional distributions usually have different contributions to the domain discrepancy. Existing methods fail to quantitatively evaluate the different importance of these two distributions, which will result in unsatisfactory transfer performance. In this article, we propose a novel concept called Dynamic Distribution Adaptation (DDA), which is capable of quantitatively evaluating the relative importance of each distribution. DDA can be easily incorporated into the framework of structural risk minimization to solve transfer learning problems. On the basis of DDA, we propose two novel learning algorithms: (1) Manifold Dynamic Distribution Adaptation (MDDA) for traditional transfer learning, and (2) Dynamic Distribution Adaptation Network (DDAN) for deep transfer learning. Extensive experiments demonstrate that MDDA and DDAN significantly improve the transfer learning performance and set up a strong baseline over the latest deep and adversarial methods on digits recognition, sentiment analysis, and image classification. More importantly, it is shown that marginal and conditional distributions have different contributions to the domain divergence, and our DDA is able to provide good quantitative evaluation of their relative importance, which leads to better performance. We believe this observation can be helpful for future research in transfer learning.

Similar Papers
  • Research Article
  • Citations15

A particle swarm optimization-based feature selection for unsupervised transfer learning

  • Jun 26, 2020
  • Soft Computing
  • Rakesh Kumar Sanodiya +4
  • Research Article
  • Citations24

Robust transfer learning based on Geometric Mean Metric Learning

  • Jun 16, 2021
  • Knowledge-Based Systems
  • Peng Zhao +3
  • Research Article
  • Citations11

Multi-Source Selection Transfer Learning with Privacy-Preserving

  • May 07, 2022
  • Neural Processing Letters
  • Weifei Wu
  • PDF
  • Research Article
  • Citations8

Normalized Recurrent Dynamic Adaption Network: A New Framework With Dynamic Alignment for Intelligent Fault Diagnosis

  • Jan 01, 2020
  • IEEE Access
  • Chengdong Zheng +4
  • PDF
  • Research Article
  • Citations40

Dynamic Distribution Adaptation Based Transfer Network for Cross Domain Bearing Fault Diagnosis

  • Jun 04, 2021
  • Chinese Journal of Mechanical Engineering
  • Yixiao Liao +4
  • Research Article
  • Citations8

Riemannian Locality Preserving Method for Transfer Learning With Applications on Brain-Computer Interface.

  • Aug 01, 2024
  • IEEE journal of biomedical and health informatics
  • Guiying Xu +6
  • Research Article
  • Citations2

Multisource Deep Transfer Learning Based on Balanced Distribution Adaptation

  • Apr 18, 2022
  • Computational Intelligence and Neuroscience
  • Peng Gao +3
  • Book Chapter
  • Citations161

Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning

  • Jan 01, 2010
  • Erheng Zhong +4
  • Research Article
  • Citations20

A novel unsupervised Globality-Locality Preserving Projections in transfer learning

  • Aug 25, 2019
  • Image and Vision Computing
  • Rakesh Kumar Sanodiya +1
  • Conference Article
  • Citations77

Dual Transfer Learning

  • Apr 26, 2012
  • Mingsheng Long +5
  • Dissertation

Label-efficient visual recognition with transfer learning

  • Jan 01, 2025
  • Jingyi Zhang
  • Conference Article
  • Citations405

Transfer Learning with Dynamic Adversarial Adaptation Network

  • Nov 01, 2019
  • Chaohui Yu +3
  • PDF
  • Research Article
  • Citations43

Multi-Source Deep Transfer Neural Network Algorithm

  • Sep 16, 2019
  • Sensors (Basel, Switzerland)
  • Jingmei Li +3
  • Research Article
  • Citations30

Deep conditional adversarial subdomain adaptation network for unsupervised mechanical fault diagnosis

  • Jun 26, 2024
  • Knowledge-Based Systems
  • Guiping Chen +4
  • Research Article
  • Citations128

A Deep Adversarial Transfer Learning Network for Machinery Emerging Fault Detection

  • Aug 01, 2020
  • IEEE Sensors Journal
  • Jipu Li +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.