mlsanityData to 7 Oct 2026

On Label Shift in Domain Adaptation via Wasserstein Distance

arXiv 2110.15520 ↗First posted 29 Oct 2021cs.LG stat.ME stat.MLcited by 2

Not on the map. Why?

Abstract (arXiv)

We study the label shift problem between the source and target domains in general domain adaptation (DA) settings. We consider transformations transporting the target to source domains, which enable us to align the source and target examples. Through those transformations, we define the label shift between two domains via optimal transport and develop theory to investigate the properties of DA under various DA settings (e.g., closed-set, partial-set, open-set, and universal settings). Inspired from the developed theory, we propose Label and Data Shift Reduction via Optimal Transport (LDROT) which can mitigate the data and label shifts simultaneously. Finally, we conduct comprehensive experiments to verify our theoretical findings and compare LDROT with state-of-the-art baselines.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

29 of 51 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  5. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  6. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  7. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  8. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  9. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  10. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  11. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  12. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
17 more
  1. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  2. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  3. 2018DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptationcited by 212
  4. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 205
  5. 2016Stochastic Optimization for Large-scale Optimal Transportcited by 188
  6. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  7. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
  8. 2019Domain-Symmetric Networks for Adversarial Domain Adaptationcited by 120
  9. 2020A Unified View of Label Shift Estimationcited by 119
  10. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  11. 2019Cluster Alignment with a Teacher for Unsupervised Domain Adaptationcited by 88
  12. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
  13. 2019Learning to Transfer Examples for Partial Domain Adaptationcited by 86
  14. 2019On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithmscited by 60
  15. 2015A New PAC-Bayesian Perspective on Domain Adaptationcited by 29
  16. 2019On Scalable and Efficient Computation of Large Scale Optimal Transportcited by 29
  17. 2020Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithmcited by 29

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1.

2 papers.

  1. 2022A Unified Wasserstein Distributional Robustness Framework for Adversarial Trainingcited by 36
  2. 2024Enhancing selectivity using Wasserstein distance based reweighingcited by 0