# Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment

arXiv: https://arxiv.org/abs/1903.01689 · HTML: https://mlsanity.com/paper/1903.01689/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2019.

## Built on by (most cited first, 30 of 61)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Reconsidering Representation Alignment for Multi-view Clustering](https://mlsanity.com/paper/2103.07738/) (2021)
- [A Theory of Label Propagation for Subpopulation Shift](https://mlsanity.com/paper/2102.11203/) (2021)
- [f-Domain-Adversarial Learning: Theory and Algorithms](https://mlsanity.com/paper/2106.11344/) (2021)
- [Structural Re-weighting Improves Graph Domain Adaptation](https://mlsanity.com/paper/2306.03221/) (2023)
- [Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate](https://mlsanity.com/paper/2107.13469/) (2021)
- [Near-Optimal Linear Regression under Distribution Shift](https://mlsanity.com/paper/2106.12108/) (2021)
- [Tracking the risk of a deployed model and detecting harmful distribution shifts](https://mlsanity.com/paper/2110.06177/) (2021)
- [Task-specific Inconsistency Alignment for Domain Adaptive Object Detection](https://mlsanity.com/paper/2203.15345/) (2022)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift](https://mlsanity.com/paper/2208.01857/) (2022)
- [Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation](https://mlsanity.com/paper/2202.01336/) (2022)
- [Aggregating From Multiple Target-Shifted Sources](https://mlsanity.com/paper/2105.04051/) (2021)
- [Offline Imitation Learning with Suboptimal Demonstrations via Relaxed Distribution Matching](https://mlsanity.com/paper/2303.02569/) (2023)
- [The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization](https://mlsanity.com/paper/2204.04384/) (2022)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)
- [Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis](https://mlsanity.com/paper/2101.00318/) (2021)
- [Mapping conditional distributions for domain adaptation under generalized target shift](https://mlsanity.com/paper/2110.15057/) (2021)
- [Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models](https://mlsanity.com/paper/2111.13657/) (2021)
- [Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift](https://mlsanity.com/paper/2311.15961/) (2023)
- [Partial Identifiability for Domain Adaptation](https://mlsanity.com/paper/2306.06510/) (2023)
- [PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners](https://mlsanity.com/paper/2207.05685/) (2022)
- [The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error](https://mlsanity.com/paper/2203.11317/) (2022)
- [A Human-Centric Take on Model Monitoring](https://mlsanity.com/paper/2206.02868/) (2022)
- [FRuDA: Framework for Distributed Adversarial Domain Adaptation](https://mlsanity.com/paper/2112.13381/) (2021)
- [Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation](https://mlsanity.com/paper/2203.04156/) (2022)
- [Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models](https://mlsanity.com/paper/2306.06138/) (2023)

## Abstract (arXiv)

Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g. covariate or label shift, enable principled algorithms. Recently-proposed domain-adversarial approaches consist of aligning source and target encodings, often motivating this approach as minimizing two (of three) terms in a theoretical bound on target error. Unfortunately, this minimization can cause arbitrary increases in the third term, e.g. they can break down under shifting label distributions. We propose asymmetrically-relaxed distribution alignment, a new approach that overcomes some limitations of standard domain-adversarial algorithms. Moreover, we characterize precise assumptions under which our algorithm is theoretically principled and demonstrate empirical benefits on both synthetic and real datasets.