Neutralized Empirical Risk Minimization with Generalization Neutrality Bound
Neutralized Empirical Risk Minimization with Generalization Neutrality Bound
复制标题
具有泛化中性界限的中和经验风险最小化
DOI：
10.1007/978-3-662-44848-9_27
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
Jun Sakuma
中科院分区：
文献类型：
--
作者：
Kazuto Fukuchi;Jun Sakuma
目前，机器学习在许多人的生活和个人活动中发挥着重要作用。因此，有必要设计机器学习算法，以确保通过机器学习做出的决策或预测不会导致歧视，偏见或不公平待遇。在这项工作中，我们引入了一种新的经验风险最小化（ERM）框架的监督学习，中立的ERM（NERM），以确保获得的任何分类可以保证是中立的观点假设。更具体地说，给定一个观点假设，NERM的工作是找到一个目标假设，最大限度地减少经验风险，同时确定一个目标假设是中立的观点假设。在NERM框架内，我们推导出经验和概括中性风险的理论界限。此外，作为线性分类的NERM的实现，我们推导出一个最大间隔算法，中性支持向量机（SVM）。实验结果表明，我们的中性支持向量机在真实的数据集上显示出更好的分类性能，而不牺牲中立性保证。
Currently, machine learning plays an important role in the lives and individual activities of numerous people. Accordingly, it has become necessary to design machine learning algorithms to ensure that discrimination, biased views, or unfair treatment do not result from decision making or predictions made via machine learning. In this work, we introduce a novel empirical risk minimization (ERM) framework for supervised learning, neutralized ERM (NERM) that ensures that any classifiers obtained can be guaranteed to be neutral with respect to a viewpoint hypothesis. More specifically, given a viewpoint hypothesis, NERM works to find a target hypothesis that minimizes the empirical risk while simultaneously identifying a target hypothesis that is neutral to the viewpoint hypothesis. Within the NERM framework, we derive a theoretical bound on empirical and generalization neutrality risks. Furthermore, as a realization of NERM with linear classification, we derive a max-margin algorithm, neutral support vector machine (SVM). Experimental results show that our neutral SVM shows improved classification performance in real datasets without sacrificing the neutrality guarantee.