Abstract
Building fair deep neural networks (DNNs) is a crucial step towards achieving trustworthy artificial intelligence. Delving into deeper factors that affect the fairness of DNNs is paramount and serves as the foundation for mitigating model biases. However, current methods are limited in accurately predicting DNN biases, relying solely on the number of training samples and lacking more precise measurement tools. Here, we establish a geometric perspective for analyzing the fairness of DNNs, comprehensively exploring how DNNs internally shape the intrinsic geometric characteristics of datasets-the intrinsic dimensions (IDs) of perceptual manifolds, and the impact of IDs on the fairness of DNNs. Based on multiple findings, we propose Intrinsic Dimension Regularization (IDR), which enhances the fairness and performance of models by promoting the learning of concise and ID-balanced class perceptual manifolds. In various image recognition benchmark tests, IDR significantly mitigates model bias while improving its performance.
Abstract (translated)
建立公平的深度神经网络(DNN)是实现可靠人工智能的重要一步。深入研究影响DNN公平性的因素至关重要,并为减轻模型偏见提供基础。然而,现有方法在准确预测DNN偏见方面存在局限,仅依赖训练样本数量,缺乏更精确的测量工具。在这里,我们建立了分析DNN公平性的几何视角,全面探讨了DNN内部如何塑造数据集的固有几何特征-感知曼弗朗格的固有维度(IDs)以及ID对DNN公平性的影响。根据多个研究结果,我们提出了 Intrinsic Dimension Regularization(IDR),通过促进简洁且ID平衡的类感知曼弗朗格的学习来增强模型的公平性和性能。在各种图像识别基准测试中,IDR显著减轻了模型的偏差,同时提高了其性能。
URL
https://arxiv.org/abs/2404.13859