• Home
  • Search
  • Diversity-Based Generalization for Unsupervised Text Classification Under Domain Shift
  • Open Access IconOpen Access
  • Cite Icon3
  • https://doi.org/10.1007/978-3-030-67661-2_39Copy DOI Icon

Diversity-Based Generalization for Unsupervised Text Classification Under Domain Shift

  • Jan 1, 2021
  • Jitin Krishnan +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Domain adaptation approaches seek to learn from a source domain and generalize it to an unseen target domain. At present, the state-of-the-art unsupervised domain adaptation approaches for subjective text classification problems leverage unlabeled target data along with labeled source data. In this paper, we propose a novel method for domain adaptation of single-task text classification problems based on a simple but effective idea of diversity-based generalization that does not require unlabeled target data but still matches the state-of-the-art in performance. Diversity plays the role of promoting the model to better generalize and be indiscriminate towards domain shift by forcing the model not to rely on same features for prediction. We apply this concept on the most explainable component of neural networks, the attention layer. To generate sufficient diversity, we create a multi-head attention model and infuse a diversity constraint between the attention heads such that each head will learn differently. We further expand upon our model by tri-training and designing a procedure with an additional diversity constraint between the attention heads of the tri-trained classifiers. Extensive evaluation using the standard benchmark dataset of Amazon reviews and a newly constructed dataset of Crisis events shows that our fully unsupervised method matches with the competing baselines that uses unlabeled target data. Our results demonstrate that machine learning architectures that ensure sufficient diversity can generalize better; encouraging future research to design ubiquitously usable learning models without using unlabeled target data.

Similar Papers
  • Dissertation
  • Citations1

Domain Adaptation and Domain Generalization with Representation Learning

  • Jan 01, 2016
  • Muhammad Ghifary
  • Dissertation
  • Citations2

Domain Adaptation and Domain Generalization with Representation Learning

  • Jan 01, 2016
  • Muhammad Ghifary
  • Book Chapter
  • Citations45

Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-Efficient Cardiac Segmentation

  • Jan 01, 2020
  • Kang Li +3
  • Research Article
  • Citations83

Cross-spatiotemporal land-cover classification from VHR remote sensing images with deep learning based domain adaptation

  • Jul 18, 2022
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Muying Luo +1
  • Conference Article
  • Citations22

Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer

  • Sep 19, 2021
  • Jan-Aike Termohlen +4
  • Research Article

Trust-Aware Domain Adaptation Using Physics-Guided Reliability Learning for Cross-Condition Fault Diagnosis of Milling Machines

  • Jul 14, 2026
  • Sensors (Basel, Switzerland)
  • Saif Ullah +2
  • Research Article
  • Citations103

Disaster response aided by tweet classification with a domain adaptation approach

  • Sep 04, 2017
  • Journal of Contingencies and Crisis Management
  • Hongmin Li +3
  • Research Article
  • Citations12

Unsupervised Domain Adaptation via Discriminative Classes-Center Feature Learning in Adversarial Network

  • May 21, 2020
  • Neural Processing Letters
  • Wendong Chen +1
  • Research Article
  • Citations154

Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation.

  • Jan 01, 2019
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
  • Junlin Yang +5
  • Conference Article
  • Citations7

Adversarial domain adaptation for multi-device retinal OCT segmentation

  • Mar 10, 2020
  • Yufan He +5
  • PDF
  • Research Article
  • Citations33

Multi-View Collaborative Learning for Semi-Supervised Domain Adaptation

  • Jan 01, 2021
  • IEEE Access
  • Ba Hung Ngo +3
  • Research Article
  • Citations19

Source-free domain adaptation with unrestricted source hypothesis

  • Jan 08, 2024
  • Pattern Recognition
  • Jiujun He +3
  • Research Article

Few-Shot Unsupervised Domain Adaptation Based on Refined Bi-Directional Prototypical Contrastive Learning for Cross-Scene Hyperspectral Image Classification

  • Jul 04, 2025
  • Remote Sensing
  • Xuebin Tang +6
  • Research Article
  • Citations20

A novel unsupervised Globality-Locality Preserving Projections in transfer learning

  • Aug 25, 2019
  • Image and Vision Computing
  • Rakesh Kumar Sanodiya +1
  • Research Article
  • Citations13

Open-Set Hypothesis Transfer With Semantic Consistency.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Zeyu Feng +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.