mlsanityData to 7 Oct 2026

Adversarial Support Alignment

arXiv 2203.08908 ↗First posted 16 Mar 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We study the problem of aligning the supports of distributions. Compared to the existing work on distribution alignment, support alignment does not require the densities to be matched. We propose symmetric support difference as a divergence measure to quantify the mismatch between supports. We show that select discriminators (e.g. discriminator trained for Jensen-Shannon divergence) are able to map support differences as support differences in their one-dimensional output space. Following this result, our method aligns supports by minimizing a symmetrized relaxed optimal transport cost in the discriminator 1D space via an adversarial process. Furthermore, we show that our approach can be viewed as a limit of existing notions of alignment by increasing transportation assignment tolerance. We quantitatively evaluate the method across domain adaptation tasks with shifts in label distributions. Our experiments show that the proposed method is more robust against these shifts than other alignment-based baselines.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 37 of its 67 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

37 of 67 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  9. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  10. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  11. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  12. 2016Least Squares Generative Adversarial Networkscited by 1,000
25 more
  1. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  2. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  3. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  4. 2017VisDA: The Visual Domain Adaptation Challengecited by 432
  5. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  6. 2017Learning Generative Models with Sinkhorn Divergencescited by 310
  7. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  8. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  9. 2018Multi-Adversarial Domain Adaptationcited by 195
  10. 2020Domain Adaptation with Conditional Distribution Matching and Generalized Label Shiftcited by 124
  11. 2018Improving GANs Using Optimal Transportcited by 122
  12. 2019Max-Sliced Wasserstein Distance and its use for GANscited by 118
  13. 2018Adversarially Learned Anomaly Detectioncited by 115
  14. 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
  15. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
  16. 2020Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptationcited by 86
  17. 2014Domain-Adversarial Neural Networkscited by 78
  18. 2019Domain Adaptation with Asymmetrically-Relaxed Distribution Alignmentcited by 61
  19. 2019Sliced Wasserstein Generative Modelscited by 61
  20. 2021Point-set Distances for Learning Representations of 3D Point Cloudscited by 48
  21. 2018Co-regularized Alignment for Unsupervised Domain Adaptationcited by 39
  22. 2020Rethinking Distributional Matching Based Domain Adaptationcited by 33
  23. 2017Robust, Deep and Inductive Anomaly Detectioncited by 24
  24. 2020Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignmentcited by 24
  25. 2019Batch weight for domain adaptation with mass shiftcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 0; 2025: 0; 2026: 1.

5 papers.

  1. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  2. 2023Partial Identifiability for Domain Adaptationcited by 14
  3. 2023Are demographically invariant models and representations in medical imaging fair?cited by 6
  4. 2023CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shiftcited by 3
  5. 2026Is invariance all you need for algorithmic fairness? Removing demographic information can create new biascited by 0