# Zero-Round Active Learning

arXiv: https://arxiv.org/abs/2107.06703 · HTML: https://mlsanity.com/paper/2107.06703/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 14 Jul 2021.

## Builds on (most cited first, 20 of 20)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (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)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning](https://mlsanity.com/paper/2012.10630/) (2020)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Unsupervised Domain Adaptation through Self-Supervision](https://mlsanity.com/paper/1909.11825/) (2019)
- [Lazier Than Lazy Greedy](https://mlsanity.com/paper/1409.7938/) (2014)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [One-Round Active Learning](https://mlsanity.com/paper/2104.11843/) (2021)

## Built on by (most cited first, 1 of 1)

- [Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach](https://mlsanity.com/paper/2209.06995/) (2022)

## Abstract (arXiv)

Active learning (AL) aims at reducing labeling effort by identifying the most valuable unlabeled data points from a large pool. Traditional AL frameworks have two limitations: First, they perform data selection in a multi-round manner, which is time-consuming and impractical. Second, they usually assume that there are a small amount of labeled data points available in the same domain as the data in the unlabeled pool. Recent work proposes a solution for one-round active learning based on data utility learning and optimization, which fixes the first issue but still requires the initially labeled data points in the same domain. In this paper, we propose D2ULO as a solution that solves both issues. Specifically, D2ULO leverages the idea of domain adaptation (DA) to train a data utility model which can effectively predict the utility for any given unlabeled data in the target domain once labeled. The trained data utility model can then be used to select high-utility data and at the same time, provide an estimate for the utility of the selected data. Our algorithm does not rely on any feedback from annotators in the target domain and hence, can be used to perform zero-round active learning or warm-start existing multi-round active learning strategies. Our experiments show that D2ULO outperforms the existing state-of-the-art AL strategies equipped with domain adaptation over various domain shift settings (e.g., real-to-real data and synthetic-to-real data). Particularly, D2ULO is applicable to the scenario where source and target labels have mismatches, which is not supported by the existing works.