# Fairer and More Accurate Tabular Models Through NAS

arXiv: https://arxiv.org/abs/2310.12145 · HTML: https://mlsanity.com/paper/2310.12145/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 56 references that are in the map.
- First posted on arXiv 18 Oct 2023.

## Builds on (most cited first, 30 of 33)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [A Reductions Approach to Fair Classification](https://mlsanity.com/paper/1803.02453/) (2018)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [A comparative study of fairness-enhancing interventions in machine learning](https://mlsanity.com/paper/1802.04422/) (2018)
- [Understanding and Robustifying Differentiable Architecture Search](https://mlsanity.com/paper/1909.09656/) (2019)
- [Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices](https://mlsanity.com/paper/1906.09208/) (2019)
- [Fair Regression: Quantitative Definitions and Reduction-based Algorithms](https://mlsanity.com/paper/1905.12843/) (2019)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [An Empirical Study of Rich Subgroup Fairness for Machine Learning](https://mlsanity.com/paper/1808.08166/) (2018)
- [Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning](https://mlsanity.com/paper/2006.12621/) (2020)
- [Fair Bayesian Optimization](https://mlsanity.com/paper/2006.05109/) (2020)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [Multi-objective Asynchronous Successive Halving](https://mlsanity.com/paper/2106.12639/) (2021)
- [A Deep Dive into Dataset Imbalance and Bias in Face Identification](https://mlsanity.com/paper/2203.08235/) (2022)

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

- [Multi-objective Differentiable Neural Architecture Search](https://mlsanity.com/paper/2402.18213/) (2024)
- [DemOpts: Fairness corrections in COVID-19 case prediction models](https://mlsanity.com/paper/2405.09483/) (2024)
- [Automated Model Design using Gated Neuron Selection in Telecom](https://mlsanity.com/paper/2602.10854/) (2026)

## Abstract (arXiv)

Making models algorithmically fairer in tabular data has been long studied, with techniques typically oriented towards fixes which usually take a neural model with an undesirable outcome and make changes to how the data are ingested, what the model weights are, or how outputs are processed. We employ an emergent and different strategy where we consider updating the model's architecture and training hyperparameters to find an entirely new model with better outcomes from the beginning of the debiasing procedure. In this work, we propose using multi-objective Neural Architecture Search (NAS) and Hyperparameter Optimization (HPO) in the first application to the very challenging domain of tabular data. We conduct extensive exploration of architectural and hyperparameter spaces (MLP, ResNet, and FT-Transformer) across diverse datasets, demonstrating the dependence of accuracy and fairness metrics of model predictions on hyperparameter combinations. We show that models optimized solely for accuracy with NAS often fail to inherently address fairness concerns. We propose a novel approach that jointly optimizes architectural and training hyperparameters in a multi-objective constraint of both accuracy and fairness. We produce architectures that consistently Pareto dominate state-of-the-art bias mitigation methods either in fairness, accuracy or both, all of this while being Pareto-optimal over hyperparameters achieved through single-objective (accuracy) optimization runs. This research underscores the promise of automating fairness and accuracy optimization in deep learning models.