论文标题
对反事实公平的因果限制的解开代表
Disentangled Representation with Causal Constraints for Counterfactual Fairness
论文作者
论文摘要
许多研究都致力于学习公平代表的问题。但是，它们并未明确表示潜在表示之间的关系。在许多实际应用中，潜在表示之间可能存在因果关系。此外，大多数公平表示学习方法的重点是群体级别的公平性，并基于相关性，忽略了数据基础的因果关系。在这项工作中，我们从理论上证明，使用结构化表示形式可以使下游预测模型实现反事实公平，然后我们提出了反事实公平性变异自动编码器（CF-VAE）以获得有关域知识的结构化表示。实验结果表明，所提出的方法比基准公平方法获得了更好的公平性和准确性性能。
Much research has been devoted to the problem of learning fair representations; however, they do not explicitly the relationship between latent representations. In many real-world applications, there may be causal relationships between latent representations. Furthermore, most fair representation learning methods focus on group-level fairness and are based on correlations, ignoring the causal relationships underlying the data. In this work, we theoretically demonstrate that using the structured representations enable downstream predictive models to achieve counterfactual fairness, and then we propose the Counterfactual Fairness Variational AutoEncoder (CF-VAE) to obtain structured representations with respect to domain knowledge. The experimental results show that the proposed method achieves better fairness and accuracy performance than the benchmark fairness methods.
