This paper investigates how hate speech varies in systematic ways according to the identities it targets. Across multiple hate speech datasets annotated for targeted identities, we find that classifiers trained on hate speech targeting specific identity groups struggle to generalize to other targeted identities. This provides empirical evidence for differences in hate speech by target identity; we then investigate which patterns structure this variation. We find that the targeted demographic category (e.g. gender/sexuality or race/ethnicity) appears to have a greater effect on the language of hate speech than does the relative social power of the targeted identity group. We also find that words associated with hate speech targeting specific identities often relate to stereotypes, histories of oppression, current social movements, and other social contexts specific to identities. These experiments suggest the importance of considering targeted identity, as well as the social contexts associated with these identities, in automated hate speech classification.

该摘要提出了一种探讨了在线政治战略游戏中多党话语中的检测和建模复杂社会现象的目标建模。我们开发了一种双层方法，首先将社会语言行为编码为语言特征，然后使用强化学习来估计任何玩家提供的优势。在第一层，社会语言行为（例如友谊和推理），即友谊和推理，用于影响他人的友谊和推理被编码为语言特征，以识别每个玩家在同时双方对话中应用的说服策略。在第二层中，加强学习方法用于估计图形感知奖励功能，以量化基于它们在该多群设置中的每个播放器提供的优势。我们将这种技术应用于游戏外交，使用了在78个用户之间交换了超过15,000个消息的数据集。与上下文 - 不可知的设置相比，我们的图形感知方法显示了强大的性能。

Tiktok是一个受欢迎的新社交媒体，用户通过短视频剪辑表达自己。平台上的常见互动形式参与了“挑战”，这是用户迭代的歌曲和舞蹈。挑战传染可以通过复制范围来衡量，即用户上传他们参与挑战的视频。 Tiktok平台的唯一性，其中挑战内容和用户偏好都在不断发展，需要挑战和用户表示的组合。本文通过预测用户的参与调查Tiktok挑战的社会传染。我们提出了一种新的深度学习模型，深度学习模型，学习和组合潜在的用户和挑战表格，以执行此用户挑战预测任务。我们从Fortoupage，App的登陆页面上的12个趋势挑战收集超过7,000个视频的数据集，从1303名用户提供超过10,000个视频。进行了广泛的实验，结果表明，我们所提出的Deepballenger（F1 = 0.494）在预测任务中优于基线（F1 = 0.188）。

Domain adaptation aims to transfer the knowledge acquired by models trained on (data-rich) source domains to (low-resource) target domains, for which a popular method is invariant representation learning. While they have been studied extensively for classification and regression problems, how they apply to ranking problems, where the data and metrics have a list structure, is not well understood. Theoretically, we establish a domain adaptation generalization bound for ranking under listwise metrics such as MRR and NDCG. The bound suggests an adaptation method via learning list-level domain-invariant feature representations, whose benefits are empirically demonstrated by unsupervised domain adaptation experiments on real-world ranking tasks, including passage reranking. A key message is that for domain adaptation, the representations should be analyzed at the same level at which the metric is computed, as we show that learning invariant representations at the list level is most effective for adaptation on ranking problems.

人类机器人互动（HRI）的研究旨在建立人与机器人之间的紧密而友好的沟通。在以人为中心的HRI中，实施成功有效的HRI的一个重要方面是建立自然而直观的互动，包括口头和非语言。作为一种普遍的非言语沟通方法，在我们的日常生活中，手势和手臂手势沟通无处不在。基于手势的HRI的大量工作散布在各种研究领域。但是，仍然缺乏对基于手势的HRI作品的系统理解。本文旨在对基于手势的HRI进行全面审查，并专注于该领域的高级发现。遵循刺激和生物反应框架，该综述包括：（i）产生人类手势（刺激）。 （ii）机器人识别人类手势（有机体）。 （iii）机器人对人手势的反应（反应）。此外，本综述总结了框架中每个元素的研究状态，并分析相关工作的优势和缺点。在最后一部分中，本文讨论了有关基于手势的HRI的当前研究挑战，并提供了未来的方向。

当机器学习（ML）模型提供其培训分配以外的数据时，他们更有可能做出不准确的预测。在网络物理系统（CPS）中，这可能导致灾难性系统故障。为了减轻这种风险，分布（OOD）检测器可以与ML模型和标志输入并行运行，这可能导致不良结果。尽管OOD探测器在准确性方面进行了很好的研究，但对资源约束CPS的部署的关注较少。在这项研究中，提出了一种设计方法来调整深入OOD检测器，以满足嵌入式应用的准确性和响应时间要求。该方法使用遗传算法来优化检测器的预处理管道，并选择一种平衡鲁棒性和响应时间的量化方法。它还标识了机器人操作系统（ROS）下的几个候选任务图，以部署所选设计。该方法在两个嵌入式平台的文献中的两个基于变异自动编码器的OOD检测器上进行了证明。提供了对设计过程中发生的权衡的洞察力，并表明这种设计方法可以导致相对于不居住的OOD检测器的响应时间急剧减少，同时保持可比较的精度。

在许多情况下，需要精确的机器人操纵任务（插入，拧紧，精确选择，精确选择）。以前的方法在此类操作任务上实现了良好的性能。但是，这种方法通常需要乏味的校准或昂贵的传感器。 3D/RGB-D摄像机和扭矩/力传感器增加了机器人应用的成本，并且可能并不总是经济的。在这项工作中，我们旨在解决这些问题，但仅使用弱化和低成本的网络摄像头。我们提出了双眼对准学习（BAL），可以自动学习眼手协调和点对准能力以解决这四个任务。我们的工作重点是与未知的眼睛协调合作，并提出了自动执行眼镜校准的不同方法。该算法在模拟中进行了训练，并使用实用管道实现SIM2Real并在真实机器人上进行测试。我们的方法在四个任务上成本最低，取得了竞争性的效果。

自我关注在捕获远程关系时，在提高视觉任务的表现，例如图像分类和图像标题等方面，突出的能力。然而，自我关注模块高度依赖于查询键值特征之间的点产品乘法和维度对齐，这导致两个问题：（1）点产品乘法导致穷举和冗余计算。 （2）由于视觉特征图通常出现作为多维张量，重塑张量特征的尺度，以适应尺寸对齐可能会破坏张量特征图的内部结构。为了解决这些问题，本文提出了一种具有其变体的自我关注插入模块，即合成张量变换（STT），用于直接处理图像张量特征。如果在查询键值之间计算点 - 产品乘法，则基本STT由张量转换组成，以从视觉信息中学习合成注意力。 STT系列的有效性在图像分类和图像标题上验证。实验表明，建议的STT实现了竞争性能，同时保持鲁棒性与基于视觉任务的自我关注相比。

In this paper we explore the task of modeling (semi) structured object sequences; in particular we focus our attention on the problem of developing a structure-aware input representation for such sequences. In such sequences, we assume that each structured object is represented by a set of key-value pairs which encode the attributes of the structured object. Given a universe of keys, a sequence of structured objects can then be viewed as an evolution of the values for each key, over time. We encode and construct a sequential representation using the values for a particular key (Temporal Value Modeling - TVM) and then self-attend over the set of key-conditioned value sequences to a create a representation of the structured object sequence (Key Aggregation - KA). We pre-train and fine-tune the two components independently and present an innovative training schedule that interleaves the training of both modules with shared attention heads. We find that this iterative two part-training results in better performance than a unified network with hierarchical encoding as well as over, other methods that use a {\em record-view} representation of the sequence \cite{de2021transformers4rec} or a simple {\em flattened} representation of the sequence. We conduct experiments using real-world data to demonstrate the advantage of interleaving TVM-KA on multiple tasks and detailed ablation studies motivating our modeling choices. We find that our approach performs better than flattening sequence objects and also allows us to operate on significantly larger sequences than existing methods.

Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and ({even more importantly}) explainable predictions. Existing approaches typically explicate network outputs in a post-hoc fashion, under an implicit assumption that faithful explanations come from accurate predictions/classifications. We have an opposite claim that explanations boost (or even determine) classification. That is, end-to-end learning of explanation factors to augment discriminative representation extraction could be a more intuitive strategy to inversely assure fine-grained explainability, e.g., in those neuroimaging and neuroscience studies with high-dimensional data containing noisy, redundant, and task-irrelevant information. In this paper, we propose such an explainable geometric deep network dubbed as NeuroExplainer, with applications to uncover altered infant cortical development patterns associated with preterm birth. Given fundamental cortical attributes as network input, our NeuroExplainer adopts a hierarchical attention-decoding framework to learn fine-grained attentions and respective discriminative representations to accurately recognize preterm infants from term-born infants at term-equivalent age. NeuroExplainer learns the hierarchical attention-decoding modules under subject-level weak supervision coupled with targeted regularizers deduced from domain knowledge regarding brain development. These prior-guided constraints implicitly maximizes the explainability metrics (i.e., fidelity, sparsity, and stability) in network training, driving the learned network to output detailed explanations and accurate classifications. Experimental results on the public dHCP benchmark suggest that NeuroExplainer led to quantitatively reliable explanation results that are qualitatively consistent with representative neuroimaging studies.