最近出现了许多变异自动编码器（VAE），目的是建模多模式数据，例如，共同建模图像及其相应的标题。尽管如此，多模式的VAE倾向于仅通过在忽略标题的同时拟合图像来关注模式的子集。我们将此限制称为模态崩溃。在这项工作中，我们认为这种效果是多模式VAE训练中梯度冲突的结果。我们展示了如何检测梯度冲突（公正性块）的计算图中的子图形，以及如何利用从多任务学习到减轻模态崩溃的现有梯度冲突解决方案。也就是说，确保跨模式的公正优化。我们将培训框架应用于文献中的几种多模式VAE模型，损失和数据集，并从经验上表明，我们的框架显着改善了跨模态的潜在空间的重建性能，有条件的产生和连贯性。

实际上，决策算法通常经过表现出各种偏见的数据培训。决策者通常旨在根据假定或期望公正的基础真相目标做出决策，即同样分布在社会显着的群体中。在许多实际设置中，无法直接观察到地面真相，相反，我们必须依靠数据中的地面真相（即偏置标签）的有偏见的代理度量。此外，通常会选择性地标记数据，即，即使是有偏见的标签，也仅对获得积极决策的数据的一小部分观察到。为了克服标签和选择偏见，最近的工作提议学习随机性，通过i）在每个时间步长的在线培训新政策，ii）执行公平性作为绩效的限制。但是，现有方法仅使用标记的数据，忽略了大量未标记的数据，因此在不同时间学到的决策策略的不稳定性和差异很大。在本文中，我们提出了一种基于实用公平决策的各种自动编码器的新方法。我们的方法学习了一个无偏的数据表示，利用标记和未标记的数据，并使用表示形式在在线过程中学习策略。使用合成数据，我们从经验上验证我们的方法根据差异较低的地面真相会收敛到最佳（公平）策略。在现实世界实验中，我们进一步表明，我们的培训方法不仅提供了更稳定的学习过程，而且还产生了比以前的方法更高的公平性和效用的政策。

Automated data-driven decision making systems are increasingly being used to assist, or even replace humans in many settings. These systems function by learning from historical decisions, often taken by humans. In order to maximize the utility of these systems (or, classifiers), their training involves minimizing the errors (or, misclassifications) over the given historical data. However, it is quite possible that the optimally trained classifier makes decisions for people belonging to different social groups with different misclassification rates (e.g., misclassification rates for females are higher than for males), thereby placing these groups at an unfair disadvantage. To account for and avoid such unfairness, in this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates. We then propose intuitive measures of disparate mistreatment for decision boundary-based classifiers, which can be easily incorporated into their formulation as convex-concave constraints. Experiments on synthetic as well as real world datasets show that our methodology is effective at avoiding disparate mistreatment, often at a small cost in terms of accuracy.

Algorithmic decision making systems are ubiquitous across a wide variety of online as well as offline services. These systems rely on complex learning methods and vast amounts of data to optimize the service functionality, satisfaction of the end user and profitability. However, there is a growing concern that these automated decisions can lead, even in the absence of intent, to a lack of fairness, i.e., their outcomes can disproportionately hurt (or, benefit) particular groups of people sharing one or more sensitive attributes (e.g., race, sex). In this paper, we introduce a flexible mechanism to design fair classifiers by leveraging a novel intuitive measure of decision boundary (un)fairness. We instantiate this mechanism with two well-known classifiers, logistic regression and support vector machines, and show on real-world data that our mechanism allows for a fine-grained control on the degree of fairness, often at a small cost in terms of accuracy. A Python implementation of our mechanism is available at fate-computing.mpi-sws.org

By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance. While this capability has been demonstrated in other fields such as computer vision, natural language processing or speech recognition, it remains to be shown in robotics, where the generalization capabilities of the models are particularly critical due to the difficulty of collecting real-world robotic data. We argue that one of the keys to the success of such general robotic models lies with open-ended task-agnostic training, combined with high-capacity architectures that can absorb all of the diverse, robotic data. In this paper, we present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties. We verify our conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size, and data diversity based on a large-scale data collection on real robots performing real-world tasks. The project's website and videos can be found at robotics-transformer.github.io

The preservation, monitoring, and control of water resources has been a major challenge in recent decades. Water resources must be constantly monitored to know the contamination levels of water. To meet this objective, this paper proposes a water monitoring system using autonomous surface vehicles, equipped with water quality sensors, based on a multimodal particle swarm optimization, and the federated learning technique, with Gaussian process as a surrogate model, the AquaFeL-PSO algorithm. The proposed monitoring system has two phases, the exploration phase and the exploitation phase. In the exploration phase, the vehicles examine the surface of the water resource, and with the data acquired by the water quality sensors, a first water quality model is estimated in the central server. In the exploitation phase, the area is divided into action zones using the model estimated in the exploration phase for a better exploitation of the contamination zones. To obtain the final water quality model of the water resource, the models obtained in both phases are combined. The results demonstrate the efficiency of the proposed path planner in obtaining water quality models of the pollution zones, with a 14$\%$ improvement over the other path planners compared, and the entire water resource, obtaining a 400$\%$ better model, as well as in detecting pollution peaks, the improvement in this case study is 4,000$\%$. It was also proven that the results obtained by applying the federated learning technique are very similar to the results of a centralized system.

在接下来的十年中，社交机器人将在许多公共场所中实施，以向人类提供服务。我们质疑这些社交机器人的特性，以提供接受和自发的情感互动。更具体地说，在本研究中，我们报告了机器人在与人类参与者面对面互动任务中情绪传染中空闲运动频率的影响。机器人系统的伙伴被编程为采用悲伤的姿势和面部表情，同时讲述了三个悲伤的故事，并以低，中和高频向上/向下移动头部。每个参与者（n = 15）被邀请坐在好友面前，听故事。使用3D运动捕获系统（质量）记录了人类参与者姿势的无意识变化。结果表明，在高频试验中，肩膀/躯干在高频试验中的倾斜度更大。当Buddy以缓慢的频率移动时，自发运动的数量也更大。当两个人从事社交互动时，这些发现与实验心理学报道的结果相呼应。在Godspeed问卷中获得的分数进一步表明，当Buddy移动缓慢时，可能会发生情绪传染，因为机器人系统被认为是更自然和知识渊博的，例如，以速度与表达的情感相干。我们的工作探讨了机器人系统概念中身体姿势和空闲运动频率的重要性。这样的补充可以提供社交机器人，这些机器人在轻松的机器人人类协作任务中提供情感传染。

在胸部计算机断层扫描（CT）扫描中，自动分割地面玻璃的不透明和固结可以在高资源利用时期减轻放射科医生的负担。但是，由于分布（OOD）数据默默失败，深度学习模型在临床常规中不受信任。我们提出了一种轻巧的OOD检测方法，该方法利用特征空间中的Mahalanobis距离，并无缝集成到最新的分割管道中。简单的方法甚至可以增加具有临床相关的不确定性定量的预训练模型。我们在四个胸部CT分布偏移和两个磁共振成像应用中验证我们的方法，即海马和前列腺的分割。我们的结果表明，所提出的方法在所有探索场景中有效地检测到遥远和近型样品。

公平被广泛认为是医疗保健道德的基础。在临床决策的背景下，它取决于智力的比较忠诚（基于证据或直观），指导每个患者的管理。尽管当代机器学习的个性化力量最近引起了人们的关注，但这种认知公平是在任何决策指导的背景下，无论是传统还是创新的。然而，目前没有一般的量化框架，更不用说保证了。在这里，我们根据模型的忠诚度来制定认知公平性，这些模型是对所学的多维表述评估的，这些身份的多维表示，旨在最大程度地提高人口的捕获多样性，从而引入了代表性道德模型校准的全面框架。我们证明了该框架在来自英国生物库的大规模多模式数据上的使用来得出人口的各种表示，量化模型绩效并提出了响应良好的补救。我们提供方法作为量化和确保医疗保健认知公平的原则解决方案，并在整个研究，临床和监管领域中进行了应用。

在本文中，我们根据两个模型提出了一个端到端情感感知的对话代理：答复情绪预测模型，该模型利用对话的上下文来预测适当的情感，以便代理人在其答复中表达表达；以及一个基于预测的情感和对话的上下文的条件的文本生成模型，以产生既适合上下文又适合情感的答复。此外，我们建议使用情感分类模型来评估代理商在模型开发过程中表达的情感。这使我们能够自动评估代理。自动和人类评估结果都表明，用预定义的句子集明确指导文本生成模型导致了明确的改进，包括表达的情感和生成文本的质量。