# Unbiased Model Prediction Without Using Protected Attribute Information

arXiv: https://arxiv.org/abs/2603.29270 · HTML: https://mlsanity.com/paper/2603.29270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [A Light CNN for Deep Face Representation with Noisy Labels](https://mlsanity.com/paper/1511.02683/) (2015)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [Fair Mixup: Fairness via Interpolation](https://mlsanity.com/paper/2103.06503/) (2021)
- [Generative Adversarial Minority Oversampling](https://mlsanity.com/paper/1903.09730/) (2019)
- [Mitigating Face Recognition Bias via Group Adaptive Classifier](https://mlsanity.com/paper/2006.07576/) (2020)
- [Fairness Metrics: A Comparative Analysis](https://mlsanity.com/paper/2001.07864/) (2020)
- [Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology](https://mlsanity.com/paper/2112.14656/) (2021)
- [InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics](https://mlsanity.com/paper/2004.06592/) (2020)
- [Bias Mimicking: A Simple Sampling Approach for Bias Mitigation](https://mlsanity.com/paper/2209.15605/) (2022)
- [FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret](https://mlsanity.com/paper/2004.01355/) (2020)
- [Unravelling the Effect of Image Distortions for Biased Prediction of Pre-trained Face Recognition Models](https://mlsanity.com/paper/2108.06581/) (2021)
- [Does Data Repair Lead to Fair Models? Curating Contextually Fair Data To Reduce Model Bias](https://mlsanity.com/paper/2110.10389/) (2021)
- [Fair and accurate age prediction using distribution aware data curation and augmentation](https://mlsanity.com/paper/2009.05283/) (2020)
- [Mitigating Bias in Facial Analysis Systems by Incorporating Label Diversity](https://mlsanity.com/paper/2204.06364/) (2022)
- [Marginal Debiased Network for Fair Visual Recognition](https://mlsanity.com/paper/2401.02150/) (2024)

## Abstract (arXiv)

The problem of bias persists in the deep learning community as models continue to provide disparate performance across different demographic subgroups. Therefore, several algorithms have been proposed to improve the fairness of deep models. However, a majority of these algorithms utilize the protected attribute information for bias mitigation, which severely limits their application in real-world scenarios. To address this concern, we have proposed a novel algorithm, termed as Non-Protected Attribute-based Debiasing (NPAD) algorithm for bias mitigation, that does not require the protected attribute information. The proposed NPAD algorithm utilizes the auxiliary information provided by the non-protected attributes to optimize the model for bias mitigation. Further, two different loss functions, Debiasing via Attribute Cluster Loss (DACL) and Filter Redundancy Loss (FRL) have been proposed to optimize the model for fairness goals. Multiple experiments are performed on the LFWA and CelebA datasets for facial attribute prediction, and a significant reduction in bias across different gender and age subgroups is observed.