# Unsupervised Domain Adaptation Based on Source-guided Discrepancy

arXiv: https://arxiv.org/abs/1809.03839 · HTML: https://mlsanity.com/paper/1809.03839/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2018.

## Built on by (most cited first, 20 of 20)

- [CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2109.06165/) (2021)
- [Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improve](https://mlsanity.com/paper/2102.03924/) (2021)
- [Graph-Relational Domain Adaptation](https://mlsanity.com/paper/2202.03628/) (2022)
- [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)
- [Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation](https://mlsanity.com/paper/2203.04156/) (2022)
- [Taxonomy-Structured Domain Adaptation](https://mlsanity.com/paper/2306.07874/) (2023)
- [Lifelong Generative Modelling Using Dynamic Expansion Graph Model](https://mlsanity.com/paper/2112.08370/) (2021)
- [LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue](https://mlsanity.com/paper/2210.07777/) (2022)
- [On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space](https://mlsanity.com/paper/2302.12351/) (2023)
- [SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images](https://mlsanity.com/paper/2108.06810/) (2021)
- [Information Theory-Guided Heuristic Progressive Multi-View Coding](https://mlsanity.com/paper/2109.02344/) (2021)
- [Practicality of generalization guarantees for unsupervised domain adaptation with neural networks](https://mlsanity.com/paper/2303.08720/) (2023)
- [Towards Domain Adaptive Neural Contextual Bandits](https://mlsanity.com/paper/2406.09564/) (2024)
- [On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspective](https://mlsanity.com/paper/2507.06552/) (2025)
- [A Symmetric Loss Perspective of Reliable Machine Learning](https://mlsanity.com/paper/2101.01366/) (2021)
- [Information Theory-Guided Heuristic Progressive Multi-View Coding](https://mlsanity.com/paper/2308.10522/) (2023)
- [Improving Source-Free Target Adaptation with Vision Transformers Leveraging Domain Representation Images](https://mlsanity.com/paper/2311.12589/) (2023)
- [A Weight-aware-based Multi-source Unsupervised Domain Adaptation Method for Human Motion Intention Recognition](https://mlsanity.com/paper/2404.15366/) (2024)
- [SWDL: Stratum-Wise Difference Learning with Deep Laplacian Pyramid for Semi-Supervised 3D Intracranial Hemorrhage Segmentation](https://mlsanity.com/paper/2506.10325/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation is the problem setting where data generating distributions in the source and target domains are different, and labels in the target domain are unavailable. One important question in unsupervised domain adaptation is how to measure the difference between the source and target domains. A previously proposed discrepancy that does not use the source domain labels requires high computational cost to estimate and may lead to a loose generalization error bound in the target domain. To mitigate these problems, we propose a novel discrepancy called source-guided discrepancy (S-disc), which exploits labels in the source domain. As a consequence, S-disc can be computed efficiently with a finite sample convergence guarantee. In addition, we show that S-disc can provide a tighter generalization error bound than the one based on an existing discrepancy. Finally, we report experimental results that demonstrate the advantages of S-disc over the existing discrepancies.