# A Meta-Learning Approach to One-Step Active Learning

arXiv: https://arxiv.org/abs/1706.08334 · HTML: https://mlsanity.com/paper/1706.08334/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2017.

## Built on by (most cited first, 9 of 9)

- [Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach](https://mlsanity.com/paper/2106.02968/) (2021)
- [Partition-Based Active Learning for Graph Neural Networks](https://mlsanity.com/paper/2201.09391/) (2022)
- [A Survey of Dataset Refinement for Problems in Computer Vision Datasets](https://mlsanity.com/paper/2210.11717/) (2022)
- [A Survey on Active Deep Learning: From Model-driven to Data-driven](https://mlsanity.com/paper/2101.09933/) (2021)
- [MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning](https://mlsanity.com/paper/2103.14339/) (2021)
- [Performance-guided Reinforced Active Learning for Object Detection](https://mlsanity.com/paper/2601.15688/) (2026)
- [DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification](https://mlsanity.com/paper/2308.00146/) (2023)
- [Taming Small-sample Bias in Low-budget Active Learning](https://mlsanity.com/paper/2306.11056/) (2023)
- [Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detection](https://mlsanity.com/paper/2310.08387/) (2023)

## Abstract (arXiv)

We consider the problem of learning when obtaining the training labels is costly, which is usually tackled in the literature using active-learning techniques. These approaches provide strategies to choose the examples to label before or during training. These strategies are usually based on heuristics or even theoretical measures, but are not learned as they are directly used during training. We design a model which aims at textitlearning active-learning strategies using a meta-learning setting. More specifically, we consider a pool-based setting, where the system observes all the examples of the dataset of a problem and has to choose the subset of examples to label in a single shot. Experiments show encouraging results.