# Adversarial Active Learning for Deep Networks: a Margin Based Approach

arXiv: https://arxiv.org/abs/1802.09841 · HTML: https://mlsanity.com/paper/1802.09841/

## Key facts

- Cited by 158 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2018.

## Built on by (most cited first, 30 of 158)

- [Active Learning by Acquiring Contrastive Examples](https://mlsanity.com/paper/2109.03764/) (2021)
- [DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning](https://mlsanity.com/paper/2204.08499/) (2022)
- [InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning](https://mlsanity.com/paper/2303.04947/) (2023)
- [A Comparative Survey of Deep Active Learning](https://mlsanity.com/paper/2203.13450/) (2022)
- [Gone Fishing: Neural Active Learning with Fisher Embeddings](https://mlsanity.com/paper/2106.09675/) (2021)
- [Active Learning by Feature Mixing](https://mlsanity.com/paper/2203.07034/) (2022)
- [Large-scale Dataset Pruning with Dynamic Uncertainty](https://mlsanity.com/paper/2306.05175/) (2023)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [A Survey on Green Deep Learning](https://mlsanity.com/paper/2111.05193/) (2021)
- [Semi-Supervised Active Learning with Temporal Output Discrepancy](https://mlsanity.com/paper/2107.14153/) (2021)
- [Dataset Quantization](https://mlsanity.com/paper/2308.10524/) (2023)
- [Effective Evaluation of Deep Active Learning on Image Classification Tasks](https://mlsanity.com/paper/2106.15324/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Loss-Curvature Matching for Dataset Selection and Condensation](https://mlsanity.com/paper/2303.04449/) (2023)
- [On the Importance of Effectively Adapting Pretrained Language Models for Active Learning](https://mlsanity.com/paper/2104.08320/) (2021)
- [GALAXY: Graph-based Active Learning at the Extreme](https://mlsanity.com/paper/2202.01402/) (2022)
- [A Coreset Selection of Coreset Selection Literature: Introduction and Recent Advances](https://mlsanity.com/paper/2505.17799/) (2025)
- [Data Shapley Valuation for Efficient Batch Active Learning](https://mlsanity.com/paper/2104.08312/) (2021)
- [Unsupervised Selective Labeling for More Effective Semi-Supervised Learning](https://mlsanity.com/paper/2110.03006/) (2021)
- [Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning](https://mlsanity.com/paper/2305.18424/) (2023)
- [Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack](https://mlsanity.com/paper/2105.00623/) (2021)
- [ALLSH: Active Learning Guided by Local Sensitivity and Hardness](https://mlsanity.com/paper/2205.04980/) (2022)
- [An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models](https://mlsanity.com/paper/2401.06692/) (2024)
- [Multi-Resolution Active Learning of Fourier Neural Operators](https://mlsanity.com/paper/2309.16971/) (2023)
- [Batch Multi-Fidelity Active Learning with Budget Constraints](https://mlsanity.com/paper/2210.12704/) (2022)
- [Streaming Active Learning with Deep Neural Networks](https://mlsanity.com/paper/2303.02535/) (2023)
- [You Only Condense Once: Two Rules for Pruning Condensed Datasets](https://mlsanity.com/paper/2310.14019/) (2023)
- [S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation](https://mlsanity.com/paper/2109.08901/) (2021)
- [Boosting Active Learning via Improving Test Performance](https://mlsanity.com/paper/2112.05683/) (2021)
- [SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning](https://mlsanity.com/paper/2405.00705/) (2024)

## Abstract (arXiv)

We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous active learning strategies scalable for deep networks were mostly based on uncertain sample selection. In this work, we focus on examples lying close to the decision boundary. Based on theoretical works on margin theory for active learning, we know that such examples may help to considerably decrease the number of annotations. While measuring the exact distance to the decision boundaries is intractable, we propose to rely on adversarial examples. We do not consider anymore them as a threat instead we exploit the information they provide on the distribution of the input space in order to approximate the distance to decision boundaries. We demonstrate empirically that adversarial active queries yield faster convergence of CNNs trained on MNIST, the Shoe-Bag and the Quick-Draw datasets.