# On Target Shift in Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/1903.06336 · HTML: https://mlsanity.com/paper/1903.06336/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2019.

## Built on by (most cited first, 12 of 12)

- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [Self-supervised Learning for Electroencephalogram: A Systematic Survey](https://mlsanity.com/paper/2401.05446/) (2024)
- [Geodesic Optimization for Predictive Shift Adaptation on EEG data](https://mlsanity.com/paper/2407.03878/) (2024)
- [Fair Classification via Domain Adaptation: A Dual Adversarial Learning Approach](https://mlsanity.com/paper/2206.03656/) (2022)
- [FineFake: A Knowledge-Enriched Dataset for Fine-Grained Multi-Domain Fake News Detection](https://mlsanity.com/paper/2404.01336/) (2024)
- [Learning Invariant Representations under General Interventions on the Response](https://mlsanity.com/paper/2208.10027/) (2022)
- [Scalable Causal Domain Adaptation](https://mlsanity.com/paper/2103.00139/) (2021)
- [Universal Domain Adaptation in Ordinal Regression](https://mlsanity.com/paper/2106.11576/) (2021)
- [Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift](https://mlsanity.com/paper/2112.10844/) (2021)
- [Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen Classification from Microscopic Images](https://mlsanity.com/paper/2311.11029/) (2023)
- [Multiple Domain Causal Networks](https://mlsanity.com/paper/2205.06791/) (2022)
- [Theory-inspired Label Shift Adaptation via Aligned Distribution Mixture](https://mlsanity.com/paper/2411.02047/) (2024)

## Abstract (arXiv)

Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to learn domain invariant feature representations through adversarial deep learning. However, label shift, where the percentage of data in each class is different between domains, has received less attention. Label shift naturally arises in many contexts, especially in behavioral studies where the behaviors are freely chosen. In this work, we propose a method called Domain Adversarial nets for Target Shift (DATS) to address label shift while learning a domain invariant representation. This is accomplished by using distribution matching to estimate label proportions in a blind test set. We extend this framework to handle multiple domains by developing a scheme to upweight source domains most similar to the target domain. Empirical results show that this framework performs well under large label shift in synthetic and real experiments, demonstrating the practical importance.