• Home
  • Search
  • A Unified Framework for Metric Transfer Learning
  • Cite Icon223
  • https://doi.org/10.1109/tkde.2017.2669193Copy DOI Icon

A Unified Framework for Metric Transfer Learning

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

Transfer learning has been proven to be effective for the problems where training data from a source domain and test data from a target domain are drawn from different distributions. To reduce the distribution divergence between the source domain and the target domain, many previous studies have been focused on designing and optimizing objective functions with the Euclidean distance to measure dissimilarity between instances. However, in some real-world applications, the Euclidean distance may be inappropriate to capture the intrinsic similarity or dissimilarity between instances. To deal with this issue, in this paper, we propose a metric transfer learning framework (MTLF) to encode metric learning in transfer learning. In MTLF, instance weights are learned and exploited to bridge the distributions of different domains, while Mahalanobis distance is learned simultaneously to maximize the intra-class distances and minimize the inter-class distances for the target domain. Unlike previous work where instance weights and Mahalanobis distance are trained in a pipelined framework that potentially leads to error propagation across different components, MTLF attempts to learn instance weights and a Mahalanobis distance in a parallel framework to make knowledge transfer across domains more effective. Furthermore, we develop general solutions to both classification and regression problems on top of MTLF, respectively. We conduct extensive experiments on several real-world datasets on object recognition, handwriting recognition, and WiFi location to verify the effectiveness of MTLF compared with a number of state-of-the-art methods.

Similar Papers
  • Research Article
  • Citations44

A framework for semi-supervised metric transfer learning on manifolds

  • Apr 01, 2019
  • Knowledge-Based Systems
  • Rakesh Kumar Sanodiya +1
  • Research Article
  • Citations34

A New Transfer Learning Algorithm in Semi-Supervised Setting

  • Jan 01, 2019
  • IEEE Access
  • Rakesh Kumar Sanodiya +3
  • Research Article
  • Citations21

Enhancing cross-subject EEG emotion recognition through multi-source manifold metric transfer learning

  • Apr 09, 2024
  • Computers in Biology and Medicine
  • Xinsheng Shi +5
  • Research Article
  • Citations53

Online transfer learning by leveraging multiple source domains

  • Jan 11, 2017
  • Knowledge and Information Systems
  • Qingyao Wu +4
  • Supplementary Content

On Transfer Learning Techniques for Machine Learning

  • Apr 30, 2020
  • Figshare
  • Debasmit Das
  • Book Chapter
  • Citations6

Semi-supervised Learning with Transfer Learning

  • Jan 01, 2013
  • Huiwei Zhou +3
  • Research Article
  • Citations378

A survey on heterogeneous transfer learning

  • Sep 26, 2017
  • Journal of Big Data
  • Oscar Day +1
  • Research Article
  • Citations4

Multi-layer transfer learning algorithm based on improved common spatial pattern for brain-computer interfaces

  • Mar 01, 2025
  • Journal of Neuroscience Methods
  • Zhuo Cai +4
  • Research Article
  • Citations24

Multi-component transfer metric learning for handling unrelated source domain samples

  • Jun 12, 2020
  • Knowledge-Based Systems
  • Chang’An Yi +4
  • Research Article
  • Citations16

Overcoming learning bias via Prototypical Feature Compensation for source-free domain adaptation

  • Sep 17, 2024
  • Pattern Recognition
  • Zicheng Pan +3
  • Research Article
  • Citations37

Reducing the effect of sample bias for small data sets with double‐weighted support vector transfer regression

  • Sep 01, 2020
  • Computer-Aided Civil and Infrastructure Engineering
  • Huan Luo +1
  • Research Article
  • Citations108

Moment matching-based intraclass multisource domain adaptation network for bearing fault diagnosis

  • Dec 09, 2021
  • Mechanical Systems and Signal Processing
  • Yu Xia +5
  • Book Chapter
  • Citations22

Transfer Learning with Multiple Sources via Consensus Regularized Autoencoders

  • Jan 01, 2014
  • Fuzhen Zhuang +5
  • PDF
  • Research Article
  • Citations8

Cross-Condition Fault Diagnosis of an Aircraft Environmental Control System (ECS) by Transfer Learning

  • Dec 09, 2023
  • Applied Sciences
  • Lilin Jia +2
  • Dissertation

Data-driven Fault Diagnosis for Cyber-Physical Systems

  • May 09, 2025
  • Mehdi Saman Azari
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.