# How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?

arXiv: https://arxiv.org/abs/2101.01104 · HTML: https://mlsanity.com/paper/2101.01104/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2020.

## Built on by (most cited first, 17 of 17)

- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [Learning Bounds for Open-Set Learning](https://mlsanity.com/paper/2106.15792/) (2021)
- [Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2105.01563/) (2021)
- [Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data](https://mlsanity.com/paper/2106.07636/) (2021)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2401.11448/) (2024)
- [Delving into the Continuous Domain Adaptation](https://mlsanity.com/paper/2208.13121/) (2022)
- [A Unified Data Representation Learning for Non-parametric Two-sample Testing](https://mlsanity.com/paper/2412.00613/) (2024)
- [Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2307.05948/) (2023)
- [Autonomous Cross Domain Adaptation under Extreme Label Scarcity](https://mlsanity.com/paper/2209.01548/) (2022)
- [Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization](https://mlsanity.com/paper/2203.05076/) (2022)
- [RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization](https://mlsanity.com/paper/2404.09530/) (2024)
- [Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning](https://mlsanity.com/paper/2112.01948/) (2021)
- [Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2201.11963/) (2022)
- [Multi-class Classification with Fuzzy-feature Observations: Theory and Algorithms](https://mlsanity.com/paper/2206.04311/) (2022)
- [Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation](https://mlsanity.com/paper/2301.08413/) (2023)
- [Source-free Semantic Regularization Learning for Semi-supervised Domain Adaptation](https://mlsanity.com/paper/2501.01126/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. Classical UDA learning bounds show that target risk is upper bounded by three terms: source risk, distribution discrepancy, and combined risk. Based on the assumption that the combined risk is a small fixed value, methods based on this bound train a target classifier by only minimizing estimators of the source risk and the distribution discrepancy. However, the combined risk may increase when minimizing both estimators, which makes the target risk uncontrollable. Hence the target classifier cannot achieve ideal performance if we fail to control the combined risk. To control the combined risk, the key challenge takes root in the unavailability of the labeled samples in the target domain. To address this key challenge, we propose a method named E-MixNet. E-MixNet employs enhanced mixup, a generic vicinal distribution, on the labeled source samples and pseudo-labeled target samples to calculate a proxy of the combined risk. Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy. Furthermore, we show that if the proxy of the combined risk is added into loss functions of four representative UDA methods, their performance is also improved.