mlsanityData to 14 Oct 2026

Is margin all you need? An extensive empirical study of active learning on tabular data

arXiv 2210.03822 ↗First posted 7 Oct 2022cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Given a labeled training set and a collection of unlabeled data, the goal of active learning (AL) is to identify the best unlabeled points to label. In this comprehensive study, we analyze the performance of a variety of AL algorithms on deep neural networks trained on 69 real-world tabular classification datasets from the OpenML-CC18 benchmark. We consider different data regimes and the effect of self-supervised model pre-training. Surprisingly, we find that the classical margin sampling technique matches or outperforms all others, including current state-of-art, in a wide range of experimental settings. To researchers, we hope to encourage rigorous benchmarking against margin, and to practitioners facing tabular data labeling constraints that hyper-parameter-free margin may often be all they need.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 14 of its 43 references that are in the map. First posted on arXiv 7 Oct 2022.

Builds on

14 of 43 references.

References · 14

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017Deep Bayesian Active Learning with Image Datacited by 819
  3. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 211
  4. 2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
  5. 2014A* Samplingcited by 151
  6. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  7. 2021Batch Active Learning at Scalecited by 127
  8. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  9. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 54
  10. 2021Active Learning at the ImageNet Scalecited by 28
  11. 2018Active Learning with Partial Feedbackcited by 27
  12. 2021Convergence of Uncertainty Sampling for Active Learningcited by 19
2 more
  1. 2019Adversarial Representation Active Learningcited by 7
  2. 2021Active Learning for Network Traffic Classification: A Technical Studycited by 5

Built on by

Cited by year

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

10 papers.

  1. 2024A Cross-Domain Benchmark for Active Learningcited by 12
  2. 2024Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classificationcited by 6
  3. 2024ALPBench: A Benchmark for Active Learning Pipelines on Tabular Datacited by 5
  4. 2023An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasetscited by 4
  5. 2025Core-Set Selection for Data-efficient Land Cover Segmentationcited by 3
  6. 2022Efficient Bayesian Updates for Deep Active Learning via Laplace Approximationscited by 2
  7. 2023Combining Self-labeling with Selective Samplingcited by 1
  8. 2025No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Successcited by 1
  9. 2023Benchmarking Multi-Domain Active Learning on Image Classificationcited by 0
  10. 2025Survey of Active Learning Hyperparameters: Insights from a Large-Scale Experimental Gridcited by 0