# Overcoming Overconfidence for Active Learning

arXiv: https://arxiv.org/abs/2308.10571 · HTML: https://mlsanity.com/paper/2308.10571/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks](https://mlsanity.com/paper/1905.11001/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost](https://mlsanity.com/paper/1910.07153/) (2019)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [Active Learning by Feature Mixing](https://mlsanity.com/paper/2203.07034/) (2022)
- [State-Relabeling Adversarial Active Learning](https://mlsanity.com/paper/2004.04943/) (2020)
- [Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective](https://mlsanity.com/paper/2111.03874/) (2021)
- [VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning](https://mlsanity.com/paper/2003.11249/) (2020)
- [The AI Index 2022 Annual Report](https://mlsanity.com/paper/2205.03468/) (2022)
- [MCDAL: Maximum Classifier Discrepancy for Active Learning](https://mlsanity.com/paper/2107.11049/) (2021)
- [SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphs](https://mlsanity.com/paper/1908.08169/) (2019)
- [Mitigating Sampling Bias and Improving Robustness in Active Learning](https://mlsanity.com/paper/2109.06321/) (2021)

## Built on by (most cited first, 3 of 3)

- [Materials-Discovery Workflows Guided by Symbolic Regression: Identifying Acid-Stable Oxides for Electrocatalysis](https://mlsanity.com/paper/2412.05947/) (2024)
- [A Critical Examination of Active Learning Workflows in Materials Science](https://mlsanity.com/paper/2601.05946/) (2026)
- [Learning Woody Clearing With Loss Alignment for Zero-Shot Regrowth and Woody Segmentation](https://mlsanity.com/paper/2608.26489/) (2026)

## Abstract (arXiv)

It is not an exaggeration to say that the recent progress in artificial intelligence technology depends on large-scale and high-quality data. Simultaneously, a prevalent issue exists everywhere: the budget for data labeling is constrained. Active learning is a prominent approach for addressing this issue, where valuable data for labeling is selected through a model and utilized to iteratively adjust the model. However, due to the limited amount of data in each iteration, the model is vulnerable to bias; thus, it is more likely to yield overconfident predictions. In this paper, we present two novel methods to address the problem of overconfidence that arises in the active learning scenario. The first is an augmentation strategy named Cross-Mix-and-Mix (CMaM), which aims to calibrate the model by expanding the limited training distribution. The second is a selection strategy named Ranked Margin Sampling (RankedMS), which prevents choosing data that leads to overly confident predictions. Through various experiments and analyses, we are able to demonstrate that our proposals facilitate efficient data selection by alleviating overconfidence, even though they are readily applicable.