Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases, and the inherent trade-off between fairness and accuracy. To address these issues, we introduce FairVIC, an innovative approach that enhances fairness in neural networks by integrating variance, invariance, and covariance terms into the loss function during training. Unlike methods that rely on predefined fairness criteria, FairVIC abstracts fairness concepts to minimise dependency on protected characteristics. We evaluate FairVIC against comparable bias mitigation techniques on benchmark datasets, considering both group and individual fairness, and conduct an ablation study on the accuracy-fairness trade-off. FairVIC demonstrates significant improvements ($\approx70\%$) in fairness across all tested metrics without compromising accuracy, thus offering a robust, generalisable solution for fair deep learning across diverse tasks and datasets.

翻译：减轻自动化决策系统中的偏见，尤其是在深度学习模型中，是一个关键挑战，这源于公平性的微妙定义、数据集特定的偏见以及公平性与准确性之间固有的权衡。为解决这些问题，我们提出了FairVIC，这是一种创新方法，通过在训练期间将方差、不变性和协方差项整合到损失函数中，来增强神经网络的公平性。与依赖预定义公平标准的方法不同，FairVIC将公平性概念抽象化，以最小化对受保护特征的依赖。我们在基准数据集上，针对群体公平性和个体公平性，将FairVIC与可比的偏见减轻技术进行了评估，并对准确性-公平性权衡进行了消融研究。FairVIC在所有测试指标上均显示出公平性的显著提升（$\approx70\%$），且未损害准确性，从而为跨不同任务和数据集的公平深度学习提供了一个稳健、可推广的解决方案。