mlsanityData to 14 Oct 2026

Deep Active Learning for Text Classification with Diverse Interpretations

arXiv 2108.10687 ↗First posted 15 Aug 2021cs.CL cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Recently, Deep Neural Networks (DNNs) have made remarkable progress for text classification, which, however, still require a large number of labeled data. To train high-performing models with the minimal annotation cost, active learning is proposed to select and label the most informative samples, yet it is still challenging to measure informativeness of samples used in DNNs. In this paper, inspired by piece-wise linear interpretability of DNNs, we propose a novel Active Learning with DivErse iNterpretations (ALDEN) approach. With local interpretations in DNNs, ALDEN identifies linearly separable regions of samples. Then, it selects samples according to their diversity of local interpretations and queries their labels. To tackle the text classification problem, we choose the word with the most diverse interpretations to represent the whole sentence. Extensive experiments demonstrate that ALDEN consistently outperforms several state-of-the-art deep active learning methods.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 15 Aug 2021.

Builds on

16 of 33 references.

References · 16

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
  5. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  6. 2017Deep Bayesian Active Learning with Image Datacited by 819
  7. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  9. 2014On the Number of Linear Regions of Deep Neural Networkscited by 381
  10. 2015Visualizing and Understanding Neural Models in NLPcited by 200
  11. 2013Maxout Networkscited by 187
  12. 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
4 more
  1. 2019Sampling Bias in Deep Active Classification: An Empirical Studycited by 36
  2. 2018Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solutioncited by 32
  3. 2016Active Learning for Speech Recognition: the Power of Gradientscited by 25
  4. 2018Active Learning for Wireless IoT Intrusion Detectioncited by 19

Built on by

Cited by year

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

5 papers.

  1. 2022TrustAL: Trustworthy Active Learning using Knowledge Distillationcited by 5
  2. 2023An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasetscited by 4
  3. 2023Are Good Explainers Secretly Human-in-the-Loop Active Learners?cited by 1
  4. 2024Interpretable Modeling of Deep Reinforcement Learning Driven Schedulingcited by 0
  5. 2025ATGen: A Framework for Active Text Generationcited by 0