README:基于公平意识分解方法的表示学习
README: REpresentation learning by fairness-Aware Disentangling MEthod
摘要:
公平表示学习的目的是编码关于受保护属性(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解纠缠变分自编码器(FD-VAE)的公平表示学习。该网络将潜在空间分解为三个子空间,每个子空间包含独立的信息:1)目标属性信息,2)受保护属性信息,3)互属性信息。在表示学习之后,通过排除具有受保护的属性信息的子空间,该解纠缠表示被用于更公平的下游分类。我们通过在CelebA和UTK Face数据集上的大量实验证明了我们模型的有效性。我们的方法优于以前的国家的最先进的方法,在平等的机会和均衡的赔率大幅度。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。