# Perturbation-Based Two-Stage Multi-Domain Active Learning

arXiv: https://arxiv.org/abs/2306.10700 · HTML: https://mlsanity.com/paper/2306.10700/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 19 Jun 2023.

## Builds on (most cited first, 11 of 11)

- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [Adversarial Active Learning for Deep Networks: a Margin Based Approach](https://mlsanity.com/paper/1802.09841/) (2018)
- [Adversarial Multi-task Learning for Text Classification](https://mlsanity.com/paper/1704.05742/) (2017)
- [Multinomial Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/1802.05694/) (2018)
- [Conditional Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2102.10176/) (2021)
- [Saliency Attack: Towards Imperceptible Black-box Adversarial Attack](https://mlsanity.com/paper/2206.01898/) (2022)
- [Multi-Domain Active Learning: Literature Review and Comparative Study](https://mlsanity.com/paper/2106.13516/) (2021)
- [Investigating Multi-source Active Learning for Natural Language Inference](https://mlsanity.com/paper/2302.06976/) (2023)

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

- [Proactive Schemes: A Survey of Adversarial Attacks for Social Good](https://mlsanity.com/paper/2409.16491/) (2024)

## Abstract (arXiv)

In multi-domain learning (MDL) scenarios, high labeling effort is required due to the complexity of collecting data from various domains. Active Learning (AL) presents an encouraging solution to this issue by annotating a smaller number of highly informative instances, thereby reducing the labeling effort. Previous research has relied on conventional AL strategies for MDL scenarios, which underutilize the domain-shared information of each instance during the selection procedure. To mitigate this issue, we propose a novel perturbation-based two-stage multi-domain active learning (P2S-MDAL) method incorporated into the well-regarded ASP-MTL model. Specifically, P2S-MDAL involves allocating budgets for domains and establishing regions for diversity selection, which are further used to select the most cross-domain influential samples in each region. A perturbation metric has been introduced to evaluate the robustness of the shared feature extractor of the model, facilitating the identification of potentially cross-domain influential samples. Experiments are conducted on three real-world datasets, encompassing both texts and images. The superior performance over conventional AL strategies shows the effectiveness of the proposed strategy. Additionally, an ablation study has been carried out to demonstrate the validity of each component. Finally, we outline several intriguing potential directions for future MDAL research, thus catalyzing the field's advancement.