• Home
  • Search
  • Discriminative Feature Adaptation via Conditional Mean Discrepancy for Cross-Domain Text Classification
  • Cite Icon4
  • https://doi.org/10.1007/978-3-030-73197-7_7Copy DOI Icon

Discriminative Feature Adaptation via Conditional Mean Discrepancy for Cross-Domain Text Classification

  • Jan 1, 2021
  • Bo Zhang +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper concerns the problem of Unsupervised Domain Adaptation (UDA) in text classification, aiming to transfer the knowledge from a source domain to a different but related target domain. Previous methods learn the discriminative feature of target domain in terms of noisy pseudo labels, which inevitably produces negative effects on training a robust model. In this paper, we propose a novel criterion Conditional Mean Discrepancy (CMD) to learn the discriminative features by matching the conditional distributions across domains. CMD embeds both the conditional distributions of source and target domains into tensor-product Hilbert space and computes Hilbert-Schmidt norm instead. We shed a new light on discriminative feature adaptation: the collective knowledge of discriminative features of different domains is naturally discovered by minimizing CMD. We propose Aligned Adaptation Networks (AAN) to learn the domain-invariant and discriminative features simultaneously based on Maximum Mean Discrepancy (MMD) and CMD. Meanwhile, to trade off between the marginal and conditional distributions, we further maximize both MMD and CMD criterions using adversarial strategy to make the features of AAN more discrepancy-invariant. To the best of our knowledge, this is the first work to definitely evaluate the shifts in the conditional distributions across domains. Experiments on cross-domain text classification demonstrate that AAN achieves better classification accuracy but less convergence time compared to the state-of-the-art deep methods.

Similar Papers
  • Research Article
  • Citations6

Cross-Domain Urban Land Use Classification via Scenewise Unsupervised Multisource Domain Adaptation With Transformer

  • Jan 01, 2024
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Mengmeng Li +3
  • Conference Article
  • Citations17

Supervised Adaptive-Transfer PLSA for Cross-Domain Text Classification

  • Dec 01, 2014
  • Rui Zhao +1
  • Research Article
  • Citations91

Unsupervised Domain Adaptation via Deep Conditional Adaptation Network

  • Oct 01, 2022
  • Pattern Recognition
  • Pengfei Ge +3
  • Research Article
  • Citations4

Domain-Invariant Feature Learning for Domain Adaptation

  • Mar 03, 2023
  • International Journal of Pattern Recognition and Artificial Intelligence
  • Ching-Ting Tu +4
  • Conference Article
  • Citations3

Modeling Sequential Domain Shift through Estimation of Optimal Sub-spaces for Categorization

  • Jan 01, 2014
  • Suranjana Samanta +2
  • Research Article
  • Citations113

Weighted and Class-Specific Maximum Mean Discrepancy for Unsupervised Domain Adaptation

  • Nov 22, 2019
  • IEEE Transactions on Multimedia
  • Hongliang Yan +5
  • Research Article
  • Citations53

Joint Clustering and Discriminative Feature Alignment for Unsupervised Domain Adaptation.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Wanxia Deng +6
  • Research Article
  • Citations5

Learning transferable and discriminative features for unsupervised domain adaptation

  • Mar 14, 2022
  • Intelligent Data Analysis
  • Yuntao Du +5
  • Conference Article
  • Citations692

Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation

  • Jul 01, 2017
  • Hongliang Yan +5
  • Research Article
  • Citations5

Domain‐specific feature recalibration and alignment for multi‐source unsupervised domain adaptation

  • Aug 27, 2022
  • IET Computer Vision
  • Mengzhu Wang +6
  • PDF
  • Conference Article
  • Citations27

Unsupervised Energy-based Adversarial Domain Adaptation for Cross-domain Text Classification

  • Jan 01, 2021
  • Han Zou +2
  • Book Chapter
  • Citations1

The $$\ell _{2,1}$$-Norm Stacked Robust Autoencoders via Adaptation Regularization for Domain Adaptation

  • Jan 01, 2019
  • Shuai Yang +4
  • Conference Article
  • Citations76

Recognizing RGB Images by Learning from RGB-D Data

  • Jun 01, 2014
  • Lin Chen +2
  • Conference Article
  • Citations4

Deep Joint Discriminative Feature Learning and Class-Aware Domain Alignment for Unsupervised Domain Adaptation

  • Feb 01, 2020
  • Han Zhao +1
  • Conference Article
  • Citations2

CANN

  • Oct 26, 2021
  • Cheng Feng +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.