以前的工作在很大程度上通过“偏见”的透镜指定的镜头考虑了图像字幕系统的公平性。相比之下，我们提供了一组技术，用于测量五种类型的代表性危害以及使用最流行的图像标题数据集获得的最终测量结果。我们的目标不是审核此图像字幕系统，而是要开发规范性的测量技术，进而提供了一个机会来反思所涉及的许多挑战。我们提出了每种危害类型的多种测量技术。我们认为，这样做可以更好地捕获每种危害的多方面性质，从而改善了所得测量值的（集体）有效性。在整个过程中，我们讨论了我们的测量方法的基础假设，并指出了它们不进行的假设。

数据对于机器学习（ML）模型的开发和评估至关重要。但是，在部署所得模型时，使用有问题或不适当的数据集可能会造成危害。为了通过对数据集进行更故意的反思和创建过程的透明度来鼓励负责任的练习，研究人员和从业人员已开始倡导增加数据文档，并提出了几个数据文档框架。但是，几乎没有研究这些数据文档框架是否满足创建和消费数据集的ML从业者的需求。为了解决这一差距，我们着手了解ML从业人员的数据文档感知，需求，挑战和Desiderata，目的是推导设计要求，以便为将来的数据文档框架提供信息。我们对一家大型国际技术公司的14名ML从业者进行了一系列半结构化访谈。我们让他们回答从数据集的数据表中提取的问题列表（Gebru，2021）。我们的发现表明，目前的数据文档方法在很大程度上是临时的，而且本质上是近视的。参与者表达了对数据文档框架的需求，可以适应其上下文，并将其集成到现有的工具和工作流程中，并尽可能自动化。尽管事实上，数据文档框架通常是从负责人的AI的角度出发的，但参与者并未在他们被要求回答的问题与负责的AI含义之间建立联系。此外，参与者通常会在数据集消费者的需求中优先考虑，并提供了不熟悉其数据集可能需要知道的信息。基于这些发现，我们为将来的数据文档框架得出了七个设计要求。

已经开发出各种工具和实践来支持从业者识别，评估和减轻AI系统造成的公平相关危害。然而，现有研究突出了这些工具和实践的预期设计与特定背景下的使用之间的差距，包括由组织因素在塑造公平工作中发挥的作用引起的差距。在本文中，我们研究了一个这样的实践的这些差距：AI系统的分类评估，旨在揭示人口统计组之间的表现差异。通过在三个技术公司的十支队伍中进行半结构化访谈和三十三名艾尔从业人员，我们在设计分列的评估时，我们识别从业者的流程，挑战，并对支持的需求。我们发现从业者在选择绩效指标时面临挑战，识别最相关的直接利益相关者和在其上进行重点的人口统计集团，并收集其进行分类评估的数据集。更一般地说，我们识别对公平工作的影响，这些工作缺乏与直接利益相关者的订婚，优先考虑通过边缘化群体的客户，以及以规模部署AI系统的驱动器。

对AI系统的分类评估，其中系统性能分别为不同的人分别评估和报告，在概念上简单。然而，他们的设计涉及各种选择。其中一些选择会影响将获得的结果，从而产生可以绘制的结论;其他人影响了有益和有害的影响 - 将分列的评估将对人们进行分类，包括其数据用于进行评估的人员。我们认为，更深入的了解这些选择将使研究人员和从业者能够设计仔细和决定性的分类评估。我们还争辩说，更好地记录这些选择，以及所做的潜在考虑因素和权衡，将在解释评估的结果和结论时帮助别人。

We survey 146 papers analyzing "bias" in NLP systems, finding that their motivations are often vague, inconsistent, and lacking in normative reasoning, despite the fact that analyzing "bias" is an inherently normative process. We further find that these papers' proposed quantitative techniques for measuring or mitigating "bias" are poorly matched to their motivations and do not engage with the relevant literature outside of NLP. Based on these findings, we describe the beginnings of a path forward by proposing three recommendations that should guide work analyzing "bias" in NLP systems. These recommendations rest on a greater recognition of the relationships between language and social hierarchies, encouraging researchers and practitioners to articulate their conceptualizations of "bias"-i.e., what kinds of system behaviors are harmful, in what ways, to whom, and why, as well as the normative reasoning underlying these statements-and to center work around the lived experiences of members of communities affected by NLP systems, while interrogating and reimagining the power relations between technologists and such communities. Anne H. Charity Hudley. 2017. Language and Racialization. In Ofelia García, Nelson Flores, and Massimiliano Spotti, editors, The Oxford Handbook of Language and Society. Oxford University Press. Won Ik Cho, Ji Won Kim, Seok Min Kim, and Nam Soo Kim. 2019. On measuring gender bias in translation of gender-neutral pronouns. In Proceedings of the Workshop on Gender Bias in Natural Language Processing, pages 173-181, Florence, Italy.

机器学习社区目前没有记录数据集的标准化过程，这可能导致高赌注域的严重后果。要解决此差距，我们提出了数据集的数据表。在电子行业，每个组件，无论多么简单或复杂，都附带了一个描述其操作特征，测试结果，推荐使用和其他信息的数据表。通过类比，我们建议每个数据集都附有一个数据表，这些表记录了它的动机，组成，收集过程，推荐用途等。数据集的数据表将有助于在数据集创建者和数据集消费者之间更好地沟通，并鼓励机器学习界优先考虑透明度和问责制。

We present a systematic approach for achieving fairness in a binary classification setting. While we focus on two well-known quantitative definitions of fairness, our approach encompasses many other previously studied definitions as special cases. The key idea is to reduce fair classification to a sequence of cost-sensitive classification problems, whose solutions yield a randomized classifier with the lowest (empirical) error subject to the desired constraints. We introduce two reductions that work for any representation of the cost-sensitive classifier and compare favorably to prior baselines on a variety of data sets, while overcoming several of their disadvantages.

The world currently offers an abundance of data in multiple domains, from which we can learn reinforcement learning (RL) policies without further interaction with the environment. RL agents learning offline from such data is possible but deploying them while learning might be dangerous in domains where safety is critical. Therefore, it is essential to find a way to estimate how a newly-learned agent will perform if deployed in the target environment before actually deploying it and without the risk of overestimating its true performance. To achieve this, we introduce a framework for safe evaluation of offline learning using approximate high-confidence off-policy evaluation (HCOPE) to estimate the performance of offline policies during learning. In our setting, we assume a source of data, which we split into a train-set, to learn an offline policy, and a test-set, to estimate a lower-bound on the offline policy using off-policy evaluation with bootstrapping. A lower-bound estimate tells us how good a newly-learned target policy would perform before it is deployed in the real environment, and therefore allows us to decide when to deploy our learned policy.

We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of an evaluation policy, $\pi_e$, using a fixed dataset, $\mathcal{D}$, collected by one or more policies that may be different from $\pi_e$. Current OPE algorithms may produce poor OPE estimates under policy distribution shift i.e., when the probability of a particular state-action pair occurring under $\pi_e$ is very different from the probability of that same pair occurring in $\mathcal{D}$ (Voloshin et al. 2021, Fu et al. 2021). In this work, we propose to improve the accuracy of OPE estimators by projecting the high-dimensional state-space into a low-dimensional state-space using concepts from the state abstraction literature. Specifically, we consider marginalized importance sampling (MIS) OPE algorithms which compute state-action distribution correction ratios to produce their OPE estimate. In the original ground state-space, these ratios may have high variance which may lead to high variance OPE. However, we prove that in the lower-dimensional abstract state-space the ratios can have lower variance resulting in lower variance OPE. We then highlight the challenges that arise when estimating the abstract ratios from data, identify sufficient conditions to overcome these issues, and present a minimax optimization problem whose solution yields these abstract ratios. Finally, our empirical evaluation on difficult, high-dimensional state-space OPE tasks shows that the abstract ratios can make MIS OPE estimators achieve lower mean-squared error and more robust to hyperparameter tuning than the ground ratios.

Reinforcement Learning (RL) can solve complex tasks but does not intrinsically provide any guarantees on system behavior. For real-world systems that fulfill safety-critical tasks, such guarantees on safety specifications are necessary. To bridge this gap, we propose a verifiably safe RL procedure with probabilistic guarantees. First, our approach probabilistically verifies a candidate controller with respect to a temporal logic specification, while randomizing the controller's inputs within a bounded set. Then, we use RL to improve the performance of this probabilistically verified, i.e. safe, controller and explore in the same bounded set around the controller's input as was randomized over in the verification step. Finally, we calculate probabilistic safety guarantees with respect to temporal logic specifications for the learned agent. Our approach is efficient for continuous action and state spaces and separates safety verification and performance improvement into two independent steps. We evaluate our approach on a safe evasion task where a robot has to evade a dynamic obstacle in a specific manner while trying to reach a goal. The results show that our verifiably safe RL approach leads to efficient learning and performance improvements while maintaining safety specifications.