# Active Few-Shot Learning with FASL

arXiv: https://arxiv.org/abs/2204.09347 · HTML: https://mlsanity.com/paper/2204.09347/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 32 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 18 of 18)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach](https://mlsanity.com/paper/1909.00161/) (2019)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [Active Learning by Acquiring Contrastive Examples](https://mlsanity.com/paper/2109.03764/) (2021)
- [The Multilingual Amazon Reviews Corpus](https://mlsanity.com/paper/2010.02573/) (2020)
- [Cold-start Active Learning through Self-supervised Language Modeling](https://mlsanity.com/paper/2010.09535/) (2020)
- [Entailment as Few-Shot Learner](https://mlsanity.com/paper/2104.14690/) (2021)
- [HEAD-QA: A Healthcare Dataset for Complex Reasoning](https://mlsanity.com/paper/1906.04701/) (2019)
- [Practical Obstacles to Deploying Active Learning](https://mlsanity.com/paper/1807.04801/) (2018)
- [Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers](https://mlsanity.com/paper/2107.05687/) (2021)
- [Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start](https://mlsanity.com/paper/2010.02584/) (2020)
- [Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning](https://mlsanity.com/paper/2012.02462/) (2020)
- [Few-Shot Learning with Siamese Networks and Label Tuning](https://mlsanity.com/paper/2203.14655/) (2022)
- [Semi-Supervised and Active Few-Shot Learning with Prototypical Networks](https://mlsanity.com/paper/1711.10856/) (2017)
- [Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasets](https://mlsanity.com/paper/2004.13138/) (2020)

## Built on by (most cited first, 11 of 11)

- [Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach](https://mlsanity.com/paper/2209.06995/) (2022)
- [Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey](https://mlsanity.com/paper/2303.08557/) (2023)
- [AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems](https://mlsanity.com/paper/2402.06287/) (2024)
- [Active Few-Shot Learning for Text Classification](https://mlsanity.com/paper/2502.18782/) (2025)
- [DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning](https://mlsanity.com/paper/2502.00305/) (2025)
- [Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settings](https://mlsanity.com/paper/2209.11481/) (2022)
- [Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling](https://mlsanity.com/paper/2311.02879/) (2023)
- [Active Transfer Prototypical Network: An Efficient Labeling Algorithm for Time-Series Data](https://mlsanity.com/paper/2209.14199/) (2022)
- [ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languages](https://mlsanity.com/paper/2502.03292/) (2025)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)
- [Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios](https://mlsanity.com/paper/2507.00330/) (2025)

## Abstract (arXiv)

Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks. However, still often thousands of examples are needed to train models with good quality. This makes it challenging to quickly develop and deploy new models for real world problems and business needs. Few-shot learning and active learning are two lines of research, aimed at tackling this problem. In this work, we combine both lines into FASL, a platform that allows training text classification models using an iterative and fast process. We investigate which active learning methods work best in our few-shot setup. Additionally, we develop a model to predict when to stop annotating. This is relevant as in a few-shot setup we do not have access to a large validation set.