# Partial Domain Adaptation without Domain Alignment

arXiv: https://arxiv.org/abs/2108.12867 · HTML: https://mlsanity.com/paper/2108.12867/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 73 references that are in the map.
- First posted on arXiv 29 Aug 2021.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [DLOW: Domain Flow for Adaptation and Generalization](https://mlsanity.com/paper/1812.05418/) (2018)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Cycle Self-Training for Domain Adaptation](https://mlsanity.com/paper/2103.03571/) (2021)
- [Visual Domain Adaptation with Manifold Embedded Distribution Alignment](https://mlsanity.com/paper/1807.07258/) (2018)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)
- [Support and Invertibility in Domain-Invariant Representations](https://mlsanity.com/paper/1903.03448/) (2019)
- [Learning to Transfer Examples for Partial Domain Adaptation](https://mlsanity.com/paper/1903.12230/) (2019)
- [Partial Transfer Learning with Selective Adversarial Networks](https://mlsanity.com/paper/1707.07901/) (2017)
- [Improved OOD Generalization via Adversarial Training and Pre-training](https://mlsanity.com/paper/2105.11144/) (2021)
- [Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1910.05562/) (2019)
- [Phase Consistent Ecological Domain Adaptation](https://mlsanity.com/paper/2004.04923/) (2020)
- [Deep Residual Correction Network for Partial Domain Adaptation](https://mlsanity.com/paper/2004.04914/) (2020)
- [Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate](https://mlsanity.com/paper/2107.13469/) (2021)
- [Rethinking Distributional Matching Based Domain Adaptation](https://mlsanity.com/paper/2006.13352/) (2020)
- [Provably Strict Generalisation Benefit for Invariance in Kernel Methods](https://mlsanity.com/paper/2106.02346/) (2021)
- [Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency](https://mlsanity.com/paper/2101.12727/) (2021)

## Built on by (most cited first, 11 of 11)

- [Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2412.11654/) (2024)
- [Unified Source-Free Domain Adaptation](https://mlsanity.com/paper/2403.07601/) (2024)
- [Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation](https://mlsanity.com/paper/2308.03097/) (2023)
- [Partial Domain Adaptation via Importance Sampling-based Shift Correction](https://mlsanity.com/paper/2507.20191/) (2025)
- [Partial Distribution Matching via Partial Wasserstein Adversarial Networks](https://mlsanity.com/paper/2409.10499/) (2024)
- [Mitigating Negative Transfer via Reducing Environmental Disagreement](https://mlsanity.com/paper/2510.24044/) (2025)
- [Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport](https://mlsanity.com/paper/2506.02712/) (2025)
- [Bi-level Unbalanced Optimal Transport for Partial Domain Adaptation](https://mlsanity.com/paper/2506.08020/) (2025)
- [Enhancing Fatigue Detection through Heterogeneous Multi-Source Data Integration and Cross-Domain Modality Imputation](https://mlsanity.com/paper/2507.16859/) (2025)
- [Domain Adaptation via Feature Refinement](https://mlsanity.com/paper/2508.16124/) (2025)
- [Locality-aware Private Class Identification for Domain Adaptation with Extreme Label Shift](https://mlsanity.com/paper/2605.05567/) (2026)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to a different but related unlabeled target domain with identical label space. Currently, the main workhorse for solving UDA is domain alignment, which has proven successful. However, it is often difficult to find an appropriate source domain with identical label space. A more practical scenario is so-called partial domain adaptation (PDA) in which the source label set or space subsumes the target one. Unfortunately, in PDA, due to the existence of the irrelevant categories in the source domain, it is quite hard to obtain a perfect alignment, thus resulting in mode collapse and negative transfer. Although several efforts have been made by down-weighting the irrelevant source categories, the strategies used tend to be burdensome and risky since exactly which irrelevant categories are unknown. These challenges motivate us to find a relatively simpler alternative to solve PDA. To achieve this, we first provide a thorough theoretical analysis, which illustrates that the target risk is bounded by both model smoothness and between-domain discrepancy. Considering the difficulty of perfect alignment in solving PDA, we turn to focus on the model smoothness while discard the riskier domain alignment to enhance the adaptability of the model. Specifically, we instantiate the model smoothness as a quite simple intra-domain structure preserving (IDSP). To our best knowledge, this is the first naive attempt to address the PDA without domain alignment. Finally, our empirical results on multiple benchmark datasets demonstrate that IDSP is not only superior to the PDA SOTAs by a significant margin on some benchmarks (e.g., +10% on Cl->Rw and +8% on Ar->Rw ), but also complementary to domain alignment in the standard UDA