Algorithmic fairness is of utmost societal importance, yet the current trend in large-scale machine learning models requires training with massive datasets that are typically biased. In this context, pre-processing methods that focus on modeling and correcting bias in the data emerge as valuable approaches. In this paper, we propose FairShap, a novel pre-processing (re-weighting) method for fair algorithmic decision-making through data valuation by means of Shapley Values. Our approach is model agnostic and easily interpretable, as it measures the contribution of each training data point to a predefined fairness metric. We empirically validate FairShap on several state-of-the-art datasets of different nature, with a variety of training scenarios and models and show how it outperforms other methods, yielding fairer models with higher or similar levels of accuracy. We also illustrate FairShap's interpretability by means of histograms and latent space visualizations. We believe that this work represents a promising direction in interpretable and model-agnostic approaches to algorithmic fairness that yield competitive accuracy even when only biased datasets are available.

翻译：算法公平性具有至关重要的社会意义，然而当前大规模机器学习模型的发展趋势要求使用通常存在偏差的海量数据集进行训练。在此背景下，专注于建模和纠正数据偏差的预处理方法成为极具价值的研究途径。本文提出FairShap——一种通过基于Shapley值的数据估值实现公平算法决策的新型预处理（重加权）方法。该方法具有模型无关性和易解释性，能够度量每个训练数据点对预定义公平性指标的贡献。我们在多个不同性质的前沿数据集上，结合多种训练场景与模型对FairShap进行了实证验证，结果表明该方法优于其他方法，能够在维持较高或相近准确率的同时得到更加公平的模型。我们还通过直方图和潜在空间可视化展示了FairShap的可解释性。我们相信，这项工作代表了可解释且模型无关的算法公平性研究方向上的一个富有前景的进展，即使在仅有偏差数据集可用的情况下，也能获得具有竞争性准确率的公平模型。