# Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation

arXiv: https://arxiv.org/abs/2312.09196 · HTML: https://mlsanity.com/paper/2312.09196/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 52 references that are in the map.
- First posted on arXiv 14 Dec 2023.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [Adversarial Active Learning for Deep Networks: a Margin Based Approach](https://mlsanity.com/paper/1802.09841/) (2018)
- [Batch Active Learning at Scale](https://mlsanity.com/paper/2107.14263/) (2021)
- [Gone Fishing: Neural Active Learning with Fisher Embeddings](https://mlsanity.com/paper/2106.09675/) (2021)
- [Deep Active Learning over the Long Tail](https://mlsanity.com/paper/1711.00941/) (2017)
- [SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios](https://mlsanity.com/paper/2107.00717/) (2021)
- [The iWildCam 2021 Competition Dataset](https://mlsanity.com/paper/2105.03494/) (2021)
- [An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits](https://mlsanity.com/paper/2006.11685/) (2020)
- [Deep Active Learning by Leveraging Training Dynamics](https://mlsanity.com/paper/2110.08611/) (2021)
- [GALAXY: Graph-based Active Learning at the Extreme](https://mlsanity.com/paper/2202.01402/) (2022)
- [Active Learning at the ImageNet Scale](https://mlsanity.com/paper/2111.12880/) (2021)
- [Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels](https://mlsanity.com/paper/2206.12569/) (2022)
- [Similarity Search for Efficient Active Learning and Search of Rare Concepts](https://mlsanity.com/paper/2007.00077/) (2020)
- [A Lagrangian Duality Approach to Active Learning](https://mlsanity.com/paper/2202.04108/) (2022)
- [Active Learning from Weak and Strong Labelers](https://mlsanity.com/paper/1510.02847/) (2015)
- [LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning](https://mlsanity.com/paper/2306.09910/) (2023)
- [Algorithm Selection for Deep Active Learning with Imbalanced Datasets](https://mlsanity.com/paper/2302.07317/) (2023)
- [Efficient and Parsimonious Agnostic Active Learning](https://mlsanity.com/paper/1506.08669/) (2015)
- [Improved Algorithms for Agnostic Pool-based Active Classification](https://mlsanity.com/paper/2105.06499/) (2021)
- [A New Perspective on Pool-Based Active Classification and False-Discovery Control](https://mlsanity.com/paper/2008.06555/) (2020)
- [Neural Active Learning on Heteroskedastic Distributions](https://mlsanity.com/paper/2211.00928/) (2022)
- [Improved Adaptive Algorithm for Scalable Active Learning with Weak Labeler](https://mlsanity.com/paper/2211.02233/) (2022)

## Built on by (most cited first, 8 of 8)

- [An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models](https://mlsanity.com/paper/2401.06692/) (2024)
- [AHA: Human-Assisted Out-of-Distribution Generalization and Detection](https://mlsanity.com/paper/2410.08000/) (2024)
- [Deep Active Learning in the Open World](https://mlsanity.com/paper/2411.06353/) (2024)
- [Active Learning with a Noisy Annotator](https://mlsanity.com/paper/2504.04506/) (2025)
- [Unique Rashomon Sets for Robust Active Learning](https://mlsanity.com/paper/2503.06770/) (2025)
- [Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance](https://mlsanity.com/paper/2606.07630/) (2026)
- [Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier](https://mlsanity.com/paper/2606.13236/) (2026)
- [Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise](https://mlsanity.com/paper/2608.13601/) (2026)

## Abstract (arXiv)

Class imbalance severely impacts machine learning performance on minority classes in real-world applications. While various solutions exist, active learning offers a fundamental fix by strategically collecting balanced, informative labeled examples from abundant unlabeled data. We introduce DIRECT, an algorithm that identifies class separation boundaries and selects the most uncertain nearby examples for annotation. By reducing the problem to one-dimensional active learning, DIRECT leverages established theory to handle batch labeling and label noise -- another common challenge in data annotation that particularly affects active learning methods. Our work presents the first comprehensive study of active learning under both class imbalance and label noise. Extensive experiments on imbalanced datasets show DIRECT reduces annotation costs by over 60% compared to state-of-the-art active learning methods and over 80% versus random sampling, while maintaining robustness to label noise.