mlsanityData to 7 Oct 2026

Active Few-Shot Learning with FASL

arXiv 2204.09347 ↗First posted 20 Apr 2022cs.CLcited by 11

Not on the map. Why?

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 20 Apr 2022.

Builds on

18 of 32 references.

References · 18

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  3. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  4. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  5. 2019Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approachcited by 299
  6. 2018Hate Speech Dataset from a White Supremacy Forumcited by 196
  7. 2021Active Learning by Acquiring Contrastive Examplescited by 154
  8. 2020The Multilingual Amazon Reviews Corpuscited by 142
  9. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  10. 2021Entailment as Few-Shot Learnercited by 122
  11. 2019HEAD-QA: A Healthcare Dataset for Complex Reasoningcited by 100
  12. 2018Practical Obstacles to Deploying Active Learningcited by 68
6 more
  1. 2021Revisiting Uncertainty-based Query Strategies for Active Learning with Transformerscited by 59
  2. 2020Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Startcited by 44
  3. 2020Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learningcited by 25
  4. 2022Few-Shot Learning with Siamese Networks and Label Tuningcited by 15
  5. 2017Semi-Supervised and Active Few-Shot Learning with Prototypical Networkscited by 8
  6. 2020Investigating the Effectiveness of Representations Based on Pretrained Transformer-based Language Models in Active Learning for Labelling Text Datasetscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 5.

11 papers.

  1. 2022Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approachcited by 16
  2. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  3. 2024AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systemscited by 7
  4. 2025Active Few-Shot Learning for Text Classificationcited by 6
  5. 2025DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learningcited by 2
  6. 2022Active Few-Shot Classification: a New Paradigm for Data-Scarce Learning Settingscited by 1
  7. 2023Exploring Active Learning in Meta-Learning: Enhancing Context Set Labelingcited by 1
  8. 2022Active Transfer Prototypical Network: An Efficient Labeling Algorithm for Time-Series Datacited by 0
  9. 2025ALPET: Active Few-shot Learning for Citation Worthiness Detection in Low-Resource Wikipedia Languagescited by 0
  10. 2025A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domainscited by 0
  11. 2025Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarioscited by 0