mlsanityData to 14 Oct 2026

REAL: A Representative Error-Driven Approach for Active Learning

arXiv 2307.00968 ↗First posted 3 Jul 2023cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Given a limited labeling budget, active learning (AL) aims to sample the most informative instances from an unlabeled pool to acquire labels for subsequent model training. To achieve this, AL typically measures the informativeness of unlabeled instances based on uncertainty and diversity. However, it does not consider erroneous instances with their neighborhood error density, which have great potential to improve the model performance. To address this limitation, we propose REAL, a novel approach to select data instances with underlineRepresentative underlineErrors for underlineActive underlineLearning. It identifies minority predictions as pseudo errors within a cluster and allocates an adaptive sampling budget for the cluster based on estimated error density. Extensive experiments on five text classification datasets demonstrate that REAL consistently outperforms all best-performing baselines regarding accuracy and F1-macro scores across a wide range of hyperparameter settings. Our analysis also shows that REAL selects the most representative pseudo errors that match the distribution of ground-truth errors along the decision boundary. Our code is publicly available at https://github.com/withchencheng/ECMLPKDD23Real.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 3 Jul 2023.

Builds on

30 of 51 references.

References · 30

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2017Billion-scale similarity search with GPUscited by 2,497
  5. 2015Character-level Convolutional Networks for Text Classificationcited by 2,330
  6. 2017Deep Bayesian Active Learning with Image Datacited by 819
  7. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  8. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  9. 2019Learning Loss for Active Learningcited by 336
  10. 2020Calibration of Pre-trained Transformerscited by 315
  11. 2020Unsupervised Domain Clusters in Pretrained Language Modelscited by 160
  12. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
18 more
  1. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  2. 2021Active Learning by Acquiring Contrastive Examplescited by 156
  3. 2020Cold-start Active Learning through Self-supervised Language Modelingcited by 128
  4. 2021Batch Active Learning at Scalecited by 127
  5. 2017PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstractscited by 124
  6. 2017Learning Active Learning from Datacited by 101
  7. 2019Discriminative Active Learningcited by 98
  8. 2017Learning how to Active Learn: A Deep Reinforcement Learning Approachcited by 79
  9. 2021Multiple instance active learning for object detectioncited by 77
  10. 2020Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!cited by 73
  11. 2017Generative Adversarial Active Learningcited by 70
  12. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  13. 2022Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topicscited by 35
  14. 2022In Defense of Core-set: A Density-aware Core-set Selection for Active Learningcited by 27
  15. 2020VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learningcited by 25
  16. 2020Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Spacecited by 17
  17. 2017Active Decision Boundary Annotation with Deep Generative Modelscited by 8
  18. 2021Loss Prediction: End-to-End Active Learning Approach For Speech Recognitioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024On the Fragility of Active Learners for Text Classificationcited by 2
  2. 2024Neural Surveillance: Live-Update Visualization of Latent Training Dynamicscited by 0
  3. 2026VisTCP: A Visualization Framework to Construct Knowledge-Graph-Based Representation for Traditional Chinese Paintingcited by 0