论文标题
Fairgrape：面部属性分类的公平感知梯度修剪方法
FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification
论文作者
论文摘要
现有的修剪技术保留了深度神经网络做出正确预测的总体能力，但在压缩过程中也可能会扩大隐藏的偏见。我们提出了一种新颖的修剪方法，即公平感知的梯度修剪法（Fairgrape），可最大程度地减少修剪对不同子组的不成比例的影响。我们的方法计算了每个模型权重的范围重要性，并选择了一部分权重，以维持相对组之间的整体修剪中的总重要性。然后，提出的方法将较小的重要性值修剪网络边缘，并通过更新重要性值来重复该过程。我们在面部属性分类的任务中证明了方法对四个不同的数据集（Fairface，utkface，celeba和Imagenet）的有效性，其中我们的方法将性能降解的差异降低了90％，而不是最先进的降级算法。我们的方法在较高的修剪率（99％）的环境中更有效。实验中使用的代码和数据集可从https://github.com/bernardo1998/fairgrape获得
Existing pruning techniques preserve deep neural networks' overall ability to make correct predictions but may also amplify hidden biases during the compression process. We propose a novel pruning method, Fairness-aware GRAdient Pruning mEthod (FairGRAPE), that minimizes the disproportionate impacts of pruning on different sub-groups. Our method calculates the per-group importance of each model weight and selects a subset of weights that maintain the relative between-group total importance in pruning. The proposed method then prunes network edges with small importance values and repeats the procedure by updating importance values. We demonstrate the effectiveness of our method on four different datasets, FairFace, UTKFace, CelebA, and ImageNet, for the tasks of face attribute classification where our method reduces the disparity in performance degradation by up to 90% compared to the state-of-the-art pruning algorithms. Our method is substantially more effective in a setting with a high pruning rate (99%). The code and dataset used in the experiments are available at https://github.com/Bernardo1998/FairGRAPE
