论文标题
README：通过公平意识解开方法的表示形式学习
README: REpresentation learning by fairness-Aware Disentangling MEthod
论文作者
论文摘要
公平代表性学习旨在编码有关受保护属性（例如性别或年龄）的不变表示。在本文中，我们设计了公平意识的分解变化自动编码器（FD-VAE），以进行公平代表学习。该网络将潜在空间置于三个子空间中，并带有去相关损失，鼓励每个子空间包含独立信息：1）目标属性信息，2）受保护的属性信息，3）相互属性信息。在表示后，通过排除使用受保护的属性信息的子空间，将这种分散的表示形式用于更公平的下游分类。我们通过对Celeba和UTK Face数据集进行了广泛的实验来证明我们的模型的有效性。我们的方法在机会均衡和均衡的赔率方面优于先前的最新方法。
Fair representation learning aims to encode invariant representation with respect to the protected attribute, such as gender or age. In this paper, we design Fairness-aware Disentangling Variational AutoEncoder (FD-VAE) for fair representation learning. This network disentangles latent space into three subspaces with a decorrelation loss that encourages each subspace to contain independent information: 1) target attribute information, 2) protected attribute information, 3) mutual attribute information. After the representation learning, this disentangled representation is leveraged for fairer downstream classification by excluding the subspace with the protected attribute information. We demonstrate the effectiveness of our model through extensive experiments on CelebA and UTK Face datasets. Our method outperforms the previous state-of-the-art method by large margins in terms of equal opportunity and equalized odds.
