# Algorithm Selection for Deep Active Learning with Imbalanced Datasets

arXiv: https://arxiv.org/abs/2302.07317 · HTML: https://mlsanity.com/paper/2302.07317/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 61 references that are in the map.
- First posted on arXiv 14 Feb 2023.

## Builds on (most cited first, 27 of 27)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Learning to Optimize Via Posterior Sampling](https://mlsanity.com/paper/1301.2609/) (2013)
- [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)
- [Learning Active Learning from Data](https://mlsanity.com/paper/1703.03365/) (2017)
- [Discriminative Active Learning](https://mlsanity.com/paper/1907.06347/) (2019)
- [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)
- [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)
- [Effective Evaluation of Deep Active Learning on Image Classification Tasks](https://mlsanity.com/paper/2106.15324/) (2021)
- [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)
- [Learning to Sample: an Active Learning Framework](https://mlsanity.com/paper/1909.03585/) (2019)
- [Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice](https://mlsanity.com/paper/1810.07778/) (2018)
- [IALE: Imitating Active Learner Ensembles](https://mlsanity.com/paper/2007.04637/) (2020)
- [ImitAL: Learning Active Learning Strategies from Synthetic Data](https://mlsanity.com/paper/2108.07670/) (2021)
- [Learning to Actively Learn: A Robust Approach](https://mlsanity.com/paper/2010.15382/) (2020)

## Built on by (most cited first, 18 of 18)

- [How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget](https://mlsanity.com/paper/2306.03543/) (2023)
- [Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separation](https://mlsanity.com/paper/2312.09196/) (2023)
- [Out-of-Distribution Learning with Human Feedback](https://mlsanity.com/paper/2408.07772/) (2024)
- [AnchorAL: Computationally Efficient Active Learning for Large and Imbalanced Datasets](https://mlsanity.com/paper/2404.05623/) (2024)
- [Deep Active Learning in the Open World](https://mlsanity.com/paper/2411.06353/) (2024)
- [Cohort-Based Active Modality Acquisition](https://mlsanity.com/paper/2505.16791/) (2025)
- [Learning from the Best: Active Learning for Wireless Communications](https://mlsanity.com/paper/2402.04896/) (2024)
- [AutoAL: Automated Active Learning with Differentiable Query Strategy Search](https://mlsanity.com/paper/2410.13853/) (2024)
- [Active Learning with Context Sampling and One-vs-Rest Entropy for Semantic Segmentation](https://mlsanity.com/paper/2412.06470/) (2024)
- [COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation](https://mlsanity.com/paper/2412.17684/) (2024)
- [Cleaning the Pool: Progressive Filtering of Unlabeled Pools in Deep Active Learning](https://mlsanity.com/paper/2511.22344/) (2025)
- [Labeled TrustSet Guided: Batch Active Learning with Reinforcement Learning](https://mlsanity.com/paper/2604.12303/) (2026)
- [Class-Balanced and Reinforced Active Learning on Graphs](https://mlsanity.com/paper/2402.10074/) (2024)
- [TS-Insight: Visualizing Thompson Sampling for Verification and XAI](https://mlsanity.com/paper/2507.19898/) (2025)
- [Active Learning with Task-Driven Representations for Messy Pools](https://mlsanity.com/paper/2510.25926/) (2025)
- [CAAL: Contextual Bandits based Online Hand-Craft Active Learning Strategy Selection](https://mlsanity.com/paper/2606.07910/) (2026)
- [ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning](https://mlsanity.com/paper/2607.29400/) (2026)
- [Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning](https://mlsanity.com/paper/2609.06806/) (2026)

## Abstract (arXiv)

Label efficiency has become an increasingly important objective in deep learning applications. Active learning aims to reduce the number of labeled examples needed to train deep networks, but the empirical performance of active learning algorithms can vary dramatically across datasets and applications. It is difficult to know in advance which active learning strategy will perform well or best in a given application. To address this, we propose the first adaptive algorithm selection strategy for deep active learning. For any unlabeled dataset, our (meta) algorithm TAILOR (Thompson ActIve Learning algORithm selection) iteratively and adaptively chooses among a set of candidate active learning algorithms. TAILOR uses novel reward functions aimed at gathering class-balanced examples. Extensive experiments in multi-class and multi-label applications demonstrate TAILOR's effectiveness in achieving accuracy comparable or better than that of the best of the candidate algorithms. Our implementation of TAILOR is open-sourced at https://github.com/jifanz/TAILOR.