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.

通过算法使表格数据的模型更公平一直以来都得到了广泛研究，但是技术一直偏向于修复不理想结果的神经模型，改变数据导入方式、模型权重或输出处理方式。本研究采用不同的策略，考虑更新模型的架构和训练超参数，从而在去偏执过程的开始找到具有更好结果的全新模型。我们首次将多目标神经架构搜索（NAS）和超参数优化（HPO) 应用于表格数据的领域，对 MLP、ResNet 和 FT-Transformer 进行了广泛的架构和超参数空间探索，展示了模型预测的准确性和公平性指标在超参数组合上的依赖关系。我们发现，仅为了准确性而经过 NAS 优化的模型往往无法固有地解决公平性问题。我们提出了一种新颖的方法，通过同时优化架构和训练超参数，以准确性和公平性的多目标约束来解决问题。我们设计了能在公平性、准确性或两者方面优于目前最先进的偏执缓解方法的模型，并在单目标（准确性）优化运行过程中达到了帕累托最优。该研究强调了在深度学习模型中自动化公平性和准确性优化的潜力。