# Fair Robust Active Learning by Joint Inconsistency

arXiv: https://arxiv.org/abs/2209.10729 · HTML: https://mlsanity.com/paper/2209.10729/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 51 references that are in the map.
- First posted on arXiv 22 Sep 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Overfitting in adversarially robust deep learning](https://mlsanity.com/paper/2002.11569/) (2020)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Parseval Networks: Improving Robustness to Adversarial Examples](https://mlsanity.com/paper/1704.08847/) (2017)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Recommendations as Treatments: Debiasing Learning and Evaluation](https://mlsanity.com/paper/1602.05352/) (2016)
- [Geometry-aware Instance-reweighted Adversarial Training](https://mlsanity.com/paper/2010.01736/) (2020)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Minimax Pareto Fairness: A Multi Objective Perspective](https://mlsanity.com/paper/2011.01821/) (2020)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning](https://mlsanity.com/paper/2006.12621/) (2020)
- [Active Sampling for Min-Max Fairness](https://mlsanity.com/paper/2006.06879/) (2020)
- [Consistency-based Active Learning for Object Detection](https://mlsanity.com/paper/2103.10374/) (2021)
- [Fair Active Learning](https://mlsanity.com/paper/2001.01796/) (2020)
- [Taking Advantage of Multitask Learning for Fair Classification](https://mlsanity.com/paper/1810.08683/) (2018)
- [Adaptive Sampling for Minimax Fair Classification](https://mlsanity.com/paper/2103.00755/) (2021)
- [Can Active Learning Preemptively Mitigate Fairness Issues?](https://mlsanity.com/paper/2104.06879/) (2021)

## Built on by (most cited first, 1 of 1)

- [Falcon: Fair Active Learning using Multi-armed Bandits](https://mlsanity.com/paper/2401.12722/) (2024)

## Abstract (arXiv)

Fairness and robustness play vital roles in trustworthy machine learning. Observing safety-critical needs in various annotation-expensive vision applications, we introduce a novel learning framework, Fair Robust Active Learning (FRAL), generalizing conventional active learning to fair and adversarial robust scenarios. This framework allows us to achieve standard and robust minimax fairness with limited acquired labels. In FRAL, we then observe existing fairness-aware data selection strategies suffer from either ineffectiveness under severe data imbalance or inefficiency due to huge computations of adversarial training. To address these two problems, we develop a novel Joint INconsistency (JIN) method exploiting prediction inconsistencies between benign and adversarial inputs as well as between standard and robust models. These two inconsistencies can be used to identify potential fairness gains and data imbalance mitigations. Thus, by performing label acquisition with our inconsistency-based ranking metrics, we can alleviate the class imbalance issue and enhance minimax fairness with limited computation. Extensive experiments on diverse datasets and sensitive groups demonstrate that our method obtains the best results in standard and robust fairness under white-box PGD attacks compared with existing active data selection baselines.