# Deep Active Learning for Text Classification with Diverse Interpretations

arXiv: https://arxiv.org/abs/2108.10687 · HTML: https://mlsanity.com/paper/2108.10687/

## 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 (most cited first, 16 of 16)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [On the Number of Linear Regions of Deep Neural Networks](https://mlsanity.com/paper/1402.1869/) (2014)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Maxout Networks](https://mlsanity.com/paper/1302.4389/) (2013)
- [Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Study](https://mlsanity.com/paper/1808.05697/) (2018)
- [Sampling Bias in Deep Active Classification: An Empirical Study](https://mlsanity.com/paper/1909.09389/) (2019)
- [Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution](https://mlsanity.com/paper/1802.06259/) (2018)
- [Active Learning for Speech Recognition: the Power of Gradients](https://mlsanity.com/paper/1612.03226/) (2016)
- [Active Learning for Wireless IoT Intrusion Detection](https://mlsanity.com/paper/1808.01412/) (2018)

## Built on by (most cited first, 5 of 5)

- [TrustAL: Trustworthy Active Learning using Knowledge Distillation](https://mlsanity.com/paper/2201.11661/) (2022)
- [An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasets](https://mlsanity.com/paper/2306.08954/) (2023)
- [Are Good Explainers Secretly Human-in-the-Loop Active Learners?](https://mlsanity.com/paper/2306.13935/) (2023)
- [Interpretable Modeling of Deep Reinforcement Learning Driven Scheduling](https://mlsanity.com/paper/2403.16293/) (2024)
- [ATGen: A Framework for Active Text Generation](https://mlsanity.com/paper/2506.23342/) (2025)

## 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.