# Corruption Robust Active Learning

arXiv: https://arxiv.org/abs/2106.11220 · HTML: https://mlsanity.com/paper/2106.11220/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 39 references that are in the map.
- First posted on arXiv 21 Jun 2021.

## Builds on (most cited first, 14 of 14)

- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise](https://mlsanity.com/paper/1802.05300/) (2018)
- [Mean estimation and regression under heavy-tailed distributions--a survey](https://mlsanity.com/paper/1906.04280/) (2019)
- [Better Algorithms for Stochastic Bandits with Adversarial Corruptions](https://mlsanity.com/paper/1902.08647/) (2019)
- [Corruption-robust exploration in episodic reinforcement learning](https://mlsanity.com/paper/1911.08689/) (2019)
- [High-Dimensional Experimental Design and Kernel Bandits](https://mlsanity.com/paper/2105.05806/) (2021)
- [Achieving Near Instance-Optimality and Minimax-Optimality in Stochastic and Adversarial Linear Bandits Simultaneously](https://mlsanity.com/paper/2102.05858/) (2021)
- [Active Learning for Cost-Sensitive Classification](https://mlsanity.com/paper/1703.01014/) (2017)
- [Active Learning under Label Shift](https://mlsanity.com/paper/2007.08479/) (2020)
- [Beyond Disagreement-based Agnostic Active Learning](https://mlsanity.com/paper/1407.2657/) (2014)
- [Taking a hint: How to leverage loss predictors in contextual bandits?](https://mlsanity.com/paper/2003.01922/) (2020)
- [Improved Corruption Robust Algorithms for Episodic Reinforcement Learning](https://mlsanity.com/paper/2102.06875/) (2021)
- [Efficient and Parsimonious Agnostic Active Learning](https://mlsanity.com/paper/1506.08669/) (2015)
- [Achieving Budget-optimality with Adaptive Schemes in Crowdsourcing](https://mlsanity.com/paper/1602.03481/) (2016)

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

- [A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits](https://mlsanity.com/paper/2202.01850/) (2022)
- [Bayesian Active Learning in the Presence of Nuisance Parameters](https://mlsanity.com/paper/2310.14968/) (2023)
- [Robust Offline Reinforcement Learning -- Certify the Confidence Interval](https://mlsanity.com/paper/2309.16631/) (2023)

## Abstract (arXiv)

We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions. In this setting, every time before the learner observes a sample, the adversary decides whether to corrupt the label or not. First, we show that, in a benign corruption setting (which includes the misspecification setting as a special case), with a slight enlargement on the hypothesis elimination threshold, the classical RobustCAL framework can (surprisingly) achieve nearly the same label complexity guarantee as in the non-corrupted setting. However, this algorithm can fail in the general corruption setting. To resolve this drawback, we propose a new algorithm which is provably correct without any assumptions on the presence of corruptions. Furthermore, this algorithm enjoys the minimax label complexity in the non-corrupted setting (which is achieved by RobustCAL) and only requires tildeO(Ctotal) additional labels in the corrupted setting to achieve O(varepsilon + fracCtotaln), where varepsilon is the target accuracy, Ctotal is the total number of corruptions and n is the total number of unlabeled samples.