Machine learning models are increasingly deployed for critical decision-making tasks, making it important to verify that they do not contain gender or racial biases picked up from training data. Typical approaches to achieve fairness revolve around efforts to clean or curate training data, with post-hoc statistical evaluation of the fairness of the model on evaluation data. In contrast, we propose techniques to \emph{prove} fairness using recently developed formal methods that verify properties of neural network models.Beyond the strength of guarantee implied by a formal proof, our methods have the advantage that we do not need explicit training or evaluation data (which is often proprietary) in order to analyze a given trained model. In experiments on two familiar datasets in the fairness literature (COMPAS and ADULTS), we show that through proper training, we can reduce unfairness by an average of 65.4\% at a cost of less than 1\% in AUC score.
translated by 谷歌翻译
知识表示和推理(KRR)系统表示知识作为事实和规则的集合。像数据库一样,KRR系统包含有关工业企业,科学和业务等人类活动领域的信息。 KRR可以代表复杂的概念和关系,它们可以以复杂的方式查询和操纵信息。不幸的是,指定必要的知识需要大多数领域专家没有的技能,而专业知识工程师很难找到,因此KRR技术受到了阻碍。一种解决方案可能是从英语文本中提取知识,并且许多作品都尝试这样做(Openseame,Google的吊索等)。不幸的是,目前,从不受限制的自然语言中提取逻辑事实仍然是不准确的,无法用于推理,而限制语言语法(所谓的受控自然语言或CNL)对于用户来说很难学习和使用。然而,与其他方法相比,一些最近基于CNL的方法,例如知识创作逻辑机(KALM)的精度非常高,并且一个自然的问题是可以在多大程度上取消CNL限制。在本文中,我们通过将KALM框架移植到神经自然语言解析器Mstanza来解决这个问题。在这里,我们将注意力限制在创作事实和查询上,因此我们的重点是我们所说的事实英语陈述。在我们的后续工作中将考虑创作其他类型的知识,例如规则。事实证明,基于神经网络的解析器有自己的问题,并且他们犯的错误范围从言论的一部分标记到lemmatization到依赖性错误。我们介绍了许多解决这些问题并测试新系统KALMFL(即,事实语言的KALM)的技术,这些技术表明KALMFL的正确性超过95%。
translated by 谷歌翻译