# Discrepancy-Based Active Learning for Domain Adaptation

arXiv: https://arxiv.org/abs/2103.03757 · HTML: https://mlsanity.com/paper/2103.03757/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 82 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Discriminative Active Learning](https://mlsanity.com/paper/1907.06347/) (2019)
- [Deep Active Learning: Unified and Principled Method for Query and Training](https://mlsanity.com/paper/1911.09162/) (2019)
- [Diverse mini-batch Active Learning](https://mlsanity.com/paper/1901.05954/) (2019)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings](https://mlsanity.com/paper/2010.08666/) (2020)
- [Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision](https://mlsanity.com/paper/1901.01151/) (2019)
- [Few-shot Domain Adaptation by Causal Mechanism Transfer](https://mlsanity.com/paper/2002.03497/) (2020)
- [Submodular Optimization with Submodular Cover and Submodular Knapsack Constraints](https://mlsanity.com/paper/1311.2106/) (2013)
- [Global optimization of Lipschitz functions](https://mlsanity.com/paper/1703.02628/) (2017)
- [On Localized Discrepancy for Domain Adaptation](https://mlsanity.com/paper/2008.06242/) (2020)
- [Active Multi-Kernel Domain Adaptation for Hyperspectral Image Classification](https://mlsanity.com/paper/1904.05200/) (2019)
- [Adaptive Region-Based Active Learning](https://mlsanity.com/paper/2002.07348/) (2020)
- [A Sub-Quadratic Exact Medoid Algorithm](https://mlsanity.com/paper/1605.06950/) (2016)

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

- [Active Learning for Domain Adaptation: An Energy-Based Approach](https://mlsanity.com/paper/2112.01406/) (2021)
- [Dirichlet-based Uncertainty Calibration for Active Domain Adaptation](https://mlsanity.com/paper/2302.13824/) (2023)
- [Combating Label Distribution Shift for Active Domain Adaptation](https://mlsanity.com/paper/2208.06604/) (2022)
- [Evidential Uncertainty Quantification: A Variance-Based Perspective](https://mlsanity.com/paper/2311.11367/) (2023)
- [Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2310.20293/) (2023)
- [Active Source Free Domain Adaptation](https://mlsanity.com/paper/2205.10711/) (2022)
- [Accelerating Batch Active Learning Using Continual Learning Techniques](https://mlsanity.com/paper/2305.06408/) (2023)
- [Generalized Universal Domain Adaptation with Generative Flow Networks](https://mlsanity.com/paper/2305.04466/) (2023)
- [Best-Effort Adaptation](https://mlsanity.com/paper/2305.05816/) (2023)
- [Cost-effective Framework for Gradual Domain Adaptation with Multifidelity](https://mlsanity.com/paper/2202.04359/) (2022)
- [Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios](https://mlsanity.com/paper/2207.01190/) (2022)
- [Certainty and Uncertainty Guided Active Domain Adaptation](https://mlsanity.com/paper/2505.19421/) (2025)
- [Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play](https://mlsanity.com/paper/2302.05807/) (2023)
- [Addressing the Cold-Start Problem for Personalized Combination Drug Screening](https://mlsanity.com/paper/2509.07850/) (2025)
- [Differentially Private Domain Adaptation with Theoretical Guarantees](https://mlsanity.com/paper/2306.08838/) (2023)
- [ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening](https://mlsanity.com/paper/2608.12219/) (2026)
- [Beyond Discrepancy: Oracle Drift in Nonstationary Weighted Risk Minimization](https://mlsanity.com/paper/2610.13598/) (2026)

## Abstract (arXiv)

The goal of the paper is to design active learning strategies which lead to domain adaptation under an assumption of Lipschitz functions. Building on previous work by Mansour et al. (2009) we adapt the concept of discrepancy distance between source and target distributions to restrict the maximization over the hypothesis class to a localized class of functions which are performing accurate labeling on the source domain. We derive generalization error bounds for such active learning strategies in terms of Rademacher average and localized discrepancy for general loss functions which satisfy a regularity condition. A practical K-medoids algorithm that can address the case of large data set is inferred from the theoretical bounds. Our numerical experiments show that the proposed algorithm is competitive against other state-of-the-art active learning techniques in the context of domain adaptation, in particular on large data sets of around one hundred thousand images.