我们介绍了精致的，这是一种有效的端到端实体链接模型，该模型使用精细的实体类型和实体描述来执行链接。该模型执行提及的检测，细粒实体键入以及单个向前传球中文档中所有提及的实体歧义，使其比现有方法快60倍以上。精制还超过了标准实体链接数据集的最先进性能，平均比3.7 F1。该模型能够将其推广到大规模的知识库，例如Wikidata（其实体是Wikipedia的15倍）和零拍的实体链接。速度，准确性和规模的结合使精制成为从网络规模数据集中提取实体的有效且具有成本效益的系统，该数据集已成功部署该模型。我们的代码和预培训模型可在https://github.com/alexa/refined上找到

We consider the problem of continually releasing an estimate of the population mean of a stream of samples that is user-level differentially private (DP). At each time instant, a user contributes a sample, and the users can arrive in arbitrary order. Until now these requirements of continual release and user-level privacy were considered in isolation. But, in practice, both these requirements come together as the users often contribute data repeatedly and multiple queries are made. We provide an algorithm that outputs a mean estimate at every time instant $t$ such that the overall release is user-level $\varepsilon$-DP and has the following error guarantee: Denoting by $M_t$ the maximum number of samples contributed by a user, as long as $\tilde{\Omega}(1/\varepsilon)$ users have $M_t/2$ samples each, the error at time $t$ is $\tilde{O}(1/\sqrt{t}+\sqrt{M}_t/t\varepsilon)$. This is a universal error guarantee which is valid for all arrival patterns of the users. Furthermore, it (almost) matches the existing lower bounds for the single-release setting at all time instants when users have contributed equal number of samples.

Soft actuators have attracted a great deal of interest in the context of rehabilitative and assistive robots for increasing safety and lowering costs as compared to rigid-body robotic systems. During actuation, soft actuators experience high levels of deformation, which can lead to microscale fractures in their elastomeric structure, which fatigues the system over time and eventually leads to macroscale damages and eventually failure. This paper reports finite element modeling (FEM) of pneu-nets at high angles, along with repetitive experimentation at high deformation rates, in order to study the effect and behavior of fatigue in soft robotic actuators, which would result in deviation from the ideal behavior. Comparing the FEM model and experimental data, we show that FEM can model the performance of the actuator before fatigue to a bending angle of 167 degrees with ~96% accuracy. We also show that the FEM model performance will drop to 80% due to fatigue after repetitive high-angle bending. The results of this paper objectively highlight the emergence of fatigue over cyclic activation of the system and the resulting deviation from the computational FEM model. Such behavior can be considered in future controllers to adapt the system with time-variable and non-autonomous response dynamics of soft robots.

As Deep Neural Networks (DNNs) are increasingly deployed in safety critical and privacy sensitive applications such as autonomous driving and biometric authentication, it is critical to understand the fault-tolerance nature of DNNs. Prior work primarily focuses on metrics such as Failures In Time (FIT) rate and the Silent Data Corruption (SDC) rate, which quantify how often a device fails. Instead, this paper focuses on quantifying the DNN accuracy given that a transient error has occurred, which tells us how well a network behaves when a transient error occurs. We call this metric Resiliency Accuracy (RA). We show that existing RA formulation is fundamentally inaccurate, because it incorrectly assumes that software variables (model weights/activations) have equal faulty probability under hardware transient faults. We present an algorithm that captures the faulty probabilities of DNN variables under transient faults and, thus, provides correct RA estimations validated by hardware. To accelerate RA estimation, we reformulate RA calculation as a Monte Carlo integration problem, and solve it using importance sampling driven by DNN specific heuristics. Using our lightweight RA estimation method, we show that transient faults lead to far greater accuracy degradation than what todays DNN resiliency tools estimate. We show how our RA estimation tool can help design more resilient DNNs by integrating it with a Network Architecture Search framework.

We present RecD (Recommendation Deduplication), a suite of end-to-end infrastructure optimizations across the Deep Learning Recommendation Model (DLRM) training pipeline. RecD addresses immense storage, preprocessing, and training overheads caused by feature duplication inherent in industry-scale DLRM training datasets. Feature duplication arises because DLRM datasets are generated from interactions. While each user session can generate multiple training samples, many features' values do not change across these samples. We demonstrate how RecD exploits this property, end-to-end, across a deployed training pipeline. RecD optimizes data generation pipelines to decrease dataset storage and preprocessing resource demands and to maximize duplication within a training batch. RecD introduces a new tensor format, InverseKeyedJaggedTensors (IKJTs), to deduplicate feature values in each batch. We show how DLRM model architectures can leverage IKJTs to drastically increase training throughput. RecD improves the training and preprocessing throughput and storage efficiency by up to 2.49x, 1.79x, and 3.71x, respectively, in an industry-scale DLRM training system.

本文研究了与可解释的AI（XAI）实践有关的两个不同但相关的问题。机器学习（ML）在金融服务中越来越重要，例如预批准，信用承销，投资以及各种前端和后端活动。机器学习可以自动检测培训数据中的非线性和相互作用，从而促进更快，更准确的信用决策。但是，机器学习模型是不透明的，难以解释，这是建立可靠技术所需的关键要素。该研究比较了各种机器学习模型，包括单个分类器（逻辑回归，决策树，LDA，QDA），异质集合（Adaboost，随机森林）和顺序神经网络。结果表明，整体分类器和神经网络的表现优于表现。此外，使用基于美国P2P贷款平台Lending Club提供的开放式访问数据集评估了两种先进的事后不可解释能力 - 石灰和外形来评估基于ML的信用评分模型。对于这项研究，我们还使用机器学习算法来开发新的投资模型，并探索可以最大化盈利能力同时最大程度地降低风险的投资组合策略。

执法和城市安全受到监视系统中的暴力事件的严重影响。尽管现代（智能）相机广泛可用且负担得起，但在大多数情况下，这种技术解决方案无能为力。此外，监测CCTV记录的人员经常显示出迟来的反应，从而导致对人和财产的灾难。因此，对迅速行动的暴力自动检测至关重要。拟议的解决方案使用了一种新颖的端到端深度学习视频视觉变压器（Vivit），可以在视频序列中熟练地辨别战斗，敌对运动和暴力事件。该研究提出了利用数据增强策略来克服较弱的电感偏见的缺点，同时在较小的培训数据集中训练视觉变压器。评估的结果随后可以发送给当地有关当局，可以分析捕获的视频。与最先进的（SOTA）相比，所提出的方法在某些具有挑战性的基准数据集上实现了吉祥的性能。

在解决复杂的现实世界任务方面的最新深度学习（DL）进步导致其在实际应用中广泛采用。但是，这个机会具有重大的潜在风险，因为这些模型中的许多模型都依赖于对各种应用程序进行培训的隐私敏感数据，这使它们成为侵犯隐私的过度暴露威胁表面。此外，基于云的机器学习-AS-A-Service（MLAAS）在其强大的基础架构支持方面的广泛使用扩大了威胁表面，以包括各种远程侧渠道攻击。在本文中，我们首先在DL实现中识别并报告了一个新颖的数据依赖性计时侧通道泄漏（称为类泄漏），该实现源自广泛使用的DL Framework Pytorch中的非恒定时间分支操作。我们进一步展示了一个实用的推理时间攻击，其中具有用户特权和硬标签黑盒访问MLAA的对手可以利用类泄漏来损害MLAAS用户的隐私。 DL模型容易受到会员推理攻击（MIA）的攻击，其中对手的目标是推断在训练模型时是否使用过任何特定数据。在本文中，作为一个单独的案例研究，我们证明了具有差异隐私保护的DL模型（对MIA的流行对策）仍然容易受到MIA的影响，而不是针对对手开发的漏洞泄漏。我们通过进行恒定的分支操作来减轻班级泄漏并有助于减轻MIA，从而开发出易于实施的对策。我们选择了两个标准基准图像分类数据集CIFAR-10和CIFAR-100来训练五个最先进的预训练的DL模型，这是在具有Intel Xeon和Intel Xeon和Intel I7处理器的两个不同的计算环境中，以验证我们的方法。

在许多应用程序（例如运动锦标赛或推荐系统）中，我们可以使用该数据，包括一组$ n $项目（或玩家）之间的成对比较。目的是使用这些数据来推断每个项目和/或其排名的潜在强度。此问题的现有结果主要集中在由单个比较图$ g $组成的设置上。但是，存在成对比较数据随时间发展的场景（例如体育比赛）。这种动态设置的理论结果相对有限，是本文的重点。我们研究\ emph {翻译同步}问题的扩展，到动态设置。在此设置中，我们给出了一系列比较图$（g_t）_ {t \ in \ mathcal {t}} $，其中$ \ nathcal {t} \ subset [0,1] $是代表时间的网格域，对于每个项目$ i $和time $ t \ in \ mathcal {t} $，有一个关联的未知强度参数$ z^*_ {t，i} \ in \ mathbb {r} $。我们的目标是恢复，以$ t \在\ Mathcal {t} $中，强度向量$ z^*_ t =（z^*_ {t，1}，\ cdots，z^*_ {t，n}） $从$ z^*_ {t，i} -z^*_ {t，j} $的噪声测量值中，其中$ \ {i，j \} $是$ g_t $中的边缘。假设$ z^*_ t $在$ t $中顺利地演变，我们提出了两个估计器 - 一个基于平滑度的最小二乘方法，另一个基于对合适平滑度操作员低频本质空间的投影。对于两个估计器，我们为$ \ ell_2 $估计错误提供有限的样本范围，假设$ g_t $已连接到\ mathcal {t} $中的所有$ t \网格尺寸$ | \ MATHCAL {T} | $。我们通过有关合成和真实数据的实验来补充理论发现。

Expression of emotions is a crucial part of daily human communication. Emotion recognition in conversations (ERC) is an emerging field of study, where the primary task is to identify the emotion behind each utterance in a conversation. Though a lot of work has been done on ERC in the past, these works only focus on ERC in the English language, thereby ignoring any other languages. In this paper, we present Multilingual MELD (M-MELD), where we extend the Multimodal EmotionLines Dataset (MELD) \cite{poria2018meld} to 4 other languages beyond English, namely Greek, Polish, French, and Spanish. Beyond just establishing strong baselines for all of these 4 languages, we also propose a novel architecture, DiscLSTM, that uses both sequential and conversational discourse context in a conversational dialogue for ERC. Our proposed approach is computationally efficient, can transfer across languages using just a cross-lingual encoder, and achieves better performance than most uni-modal text approaches in the literature on both MELD and M-MELD. We make our data and code publicly on GitHub.