In recent years, there is a surge of generation-based information extraction work, which allows a more direct use of pre-trained language models and efficiently captures output dependencies. However, previous generative methods using lexical representation do not naturally fit document-level relation extraction (DocRE) where there are multiple entities and relational facts. In this paper, we investigate the root cause of the underwhelming performance of the existing generative DocRE models and discover that the culprit is the inadequacy of the training paradigm, instead of the capacities of the models. We propose to generate a symbolic and ordered sequence from the relation matrix which is deterministic and easier for model to learn. Moreover, we design a parallel row generation method to process overlong target sequences. Besides, we introduce several negative sampling strategies to improve the performance with balanced signals. Experimental results on four datasets show that our proposed method can improve the performance of the generative DocRE models. We have released our code at https://github.com/ayyyq/DORE.
translated by 谷歌翻译
In split machine learning (ML), different partitions of a neural network (NN) are executed by different computing nodes, requiring a large amount of communication cost. To ease communication burden, over-the-air computation (OAC) can efficiently implement all or part of the computation at the same time of communication. Based on the proposed system, the system implementation over wireless network is introduced and we provide the problem formulation. In particular, we show that the inter-layer connection in a NN of any size can be mathematically decomposed into a set of linear precoding and combining transformations over MIMO channels. Therefore, the precoding matrix at the transmitter and the combining matrix at the receiver of each MIMO link, as well as the channel matrix itself, can jointly serve as a fully connected layer of the NN. The generalization of the proposed scheme to the conventional NNs is also introduced. Finally, we extend the proposed scheme to the widely used convolutional neural networks and demonstrate its effectiveness under both the static and quasi-static memory channel conditions with comprehensive simulations. In such a split ML system, the precoding and combining matrices are regarded as trainable parameters, while MIMO channel matrix is regarded as unknown (implicit) parameters.
translated by 谷歌翻译
科学文献是高质量的语料库,支持大量自然语言处理(NLP)研究。但是,现有数据集围绕英语,这限制了中国科学NLP的发展。在这项工作中,我们提出了CSL,这是一个大规模的中国科学文献数据集,其中包含396K论文的标题,摘要,关键字和学术领域。据我们所知,CSL是中文中的第一个科学文档数据集。 CSL可以用作中国语料库。同样,该半结构化数据是一种自然注释,可以构成许多监督的NLP任务。基于CSL,我们提出了一个基准,以评估跨科学领域任务的模型的性能,即摘要,关键字生成和文本分类。我们分析了现有文本到文本模型在评估任务上的行为,并揭示了中国科学NLP任务的挑战,该任务为未来的研究提供了宝贵的参考。数据和代码可在https://github.com/ydli-ai/csl上找到
translated by 谷歌翻译
机器人操作系统(ROS)为涉及生产任务,提高生产力和简化人类运营的各个领域的自动化带来了极大的自动化潜力。但是,ROS高度依赖交流,但缺乏安全的数据共享机制。确保多机器人之间的机密数据交换在多机器人交互中提出了重大挑战。在本文中,我们介绍了Authros,这是一个安全且方便的授权框架,用于ROS节点,具有绝对安全性和基于私人以太坊网络和SM算法的高可用性。据我们所知,Authros是装有ROS的机器人的第一个安全数据共享框架。该框架可以满足ROS节点之间交换机密数据的不可变性和安全性的要求。此外,提出了授权和身份验证的机制,以在没有第三方的情况下进行原子执行以确保值得信赖的数据交换。 SM2密钥交换和SM4授权加密机制均已提出用于数据传输安全性。还实施了数据摘要上传方案,以提高以太坊网络上数据查询和上传的效率。实验结果表明,它可以从6.34ms的800KB加密数据中生成摘要。通过安全分析,Authros实现了安全的数据交换,数据操作检测和节点锻造攻击保护。
translated by 谷歌翻译
密集的视频字幕旨在为未修剪视频中的一系列事件生成相应的文本描述,这些事件可以分为两个子任务,即事件检测和事件字幕。与以前分别解决这两个子任务的作品不同,最近的作品着重于增强两个子任务之间的任务间关联。但是,由于其特定于任务的解决方案的巨大差异,设计用于事件检测和字幕的任务间相互作用并不是微不足道的。此外,以前的事件检测方法通常会忽略事件之间的时间依赖性,从而导致事件冗余或不一致问题。在本文中,我们将事件检测定义为序列生成任务,并提出一个统一的预训练和微调框架,以自然增强事件检测和字幕之间的任务间关联。由于该模型将每个事件预测为以前的事件为上下文,因此事件之间的相互依赖性被充分利用,因此我们的模型可以检测到视频中更多样化和一致的事件。 ActivityNet数据集上的实验表明,我们的模型优于最新方法,并且在对大型视频文本数据进行预训练时,可以进一步提高。代码可在\ url {https://github.com/qiqang/uedvc}上获得。
translated by 谷歌翻译
作为一个严重的问题,近年来已经广泛研究了单图超分辨率(SISR)。 SISR的主要任务是恢复由退化程序引起的信息损失。根据Nyquist抽样理论,降解会导致混叠效应,并使低分辨率(LR)图像的正确纹理很难恢复。实际上,自然图像中相邻斑块之间存在相关性和自相似性。本文考虑了自相似性,并提出了一个分层图像超分辨率网络(HSRNET)来抑制混叠的影响。我们从优化的角度考虑SISR问题,并根据半季节分裂(HQS)方法提出了迭代解决方案模式。为了先验探索本地图像的质地,我们设计了一个分层探索块(HEB)并进行性增加了接受场。此外,设计多级空间注意力(MSA)是为了获得相邻特征的关系并增强了高频信息,这是视觉体验的关键作用。实验结果表明,与其他作品相比,HSRNET实现了更好的定量和视觉性能,并更有效地释放了别名。
translated by 谷歌翻译
As a critical threat to deep neural networks (DNNs), backdoor attacks can be categorized into two types, i.e., source-agnostic backdoor attacks (SABAs) and source-specific backdoor attacks (SSBAs). Compared to traditional SABAs, SSBAs are more advanced in that they have superior stealthier in bypassing mainstream countermeasures that are effective against SABAs. Nonetheless, existing SSBAs suffer from two major limitations. First, they can hardly achieve a good trade-off between ASR (attack success rate) and FPR (false positive rate). Besides, they can be effectively detected by the state-of-the-art (SOTA) countermeasures (e.g., SCAn). To address the limitations above, we propose a new class of viable source-specific backdoor attacks, coined as CASSOCK. Our key insight is that trigger designs when creating poisoned data and cover data in SSBAs play a crucial role in demonstrating a viable source-specific attack, which has not been considered by existing SSBAs. With this insight, we focus on trigger transparency and content when crafting triggers for poisoned dataset where a sample has an attacker-targeted label and cover dataset where a sample has a ground-truth label. Specifically, we implement $CASSOCK_{Trans}$ and $CASSOCK_{Cont}$. While both they are orthogonal, they are complementary to each other, generating a more powerful attack, called $CASSOCK_{Comp}$, with further improved attack performance and stealthiness. We perform a comprehensive evaluation of the three $CASSOCK$-based attacks on four popular datasets and three SOTA defenses. Compared with a representative SSBA as a baseline ($SSBA_{Base}$), $CASSOCK$-based attacks have significantly advanced the attack performance, i.e., higher ASR and lower FPR with comparable CDA (clean data accuracy). Besides, $CASSOCK$-based attacks have effectively bypassed the SOTA defenses, and $SSBA_{Base}$ cannot.
translated by 谷歌翻译
联合学习(FL)在许多分散的用户中训练全球模型,每个用户都有本地数据集。与传统的集中学习相比,FL不需要直接访问本地数据集,因此旨在减轻数据隐私问题。但是,由于推理攻击,包括成员推理,属性推理和数据反演,FL中的数据隐私泄漏仍然存在。在这项工作中,我们提出了一种新型的隐私推理攻击,创造的偏好分析攻击(PPA),它准确地介绍了本地用户的私人偏好,例如,最喜欢(不喜欢)来自客户的在线购物中的(不喜欢)项目和最常见的表达式从用户的自拍照中。通常,PPA可以在本地客户端(用户)的特征上介绍top-k(即,尤其是k = 1、2、3和k = 1)的偏好。我们的关键见解是,本地用户模型的梯度变化对给定类别的样本比例(尤其是大多数(少数)类别的样本比例具有明显的敏感性。通过观察用户模型对类的梯度敏感性,PPA可以介绍用户本地数据集中类的样本比例,从而公开用户对类的偏好。 FL的固有统计异质性进一步促进了PPA。我们使用四个数据集(MNIST,CIFAR10,RAF-DB和PRODUCTS-10K)广泛评估了PPA的有效性。我们的结果表明,PPA分别达到了MNIST和CIFAR10的90%和98%的TOP-1攻击精度。更重要的是,在实际的购物商业商业场景(即产品-10k)和社交网络(即RAF-DB)中,PPA在前一种情况下,PPA获得了78%的TOP-1攻击精度,以推断出最有序的物品(即作为商业竞争对手),在后一种情况下,有88%来推断受害者用户最常见的面部表情,例如恶心。
translated by 谷歌翻译
我们证明了深度神经网络(NNS)的损失景观的一般嵌入原理,其解除了NNS的损失景观的层次结构,即NN的损失景观包含所有较窄NN的所有关键点。通过构建一类临界嵌入来获得该结果,该临界嵌入物将较窄的Nn的任何临界点映射到具有相同输出功能的目标Nn的临界点。通过发现广泛的一般兼容性嵌入式,我们提供了嵌入来自NNS的关键点的关键子多种尺寸的总估计。我们进一步证明了任何临界嵌入的Irfreversiblility属性,即临界点的Hessian矩阵的负/零/正小叶值的数量可能增加,但由于NN通过嵌入越来越宽,因此从未减少。使用一般兼容的临界嵌入的特殊实现,我们证明了一个严格的必要条件,以便是一个完全不变的临界点,从未成为任何关键嵌入的严格鞍端。该结果暗示宽NNS中严格鞍点的常见,这可能是在实践中广泛观察到的宽NNS易于优化的重要原因。
translated by 谷歌翻译
在移动边缘网络上部署深神经网络(DNN)的主要挑战是如何分离DNN模型,以匹配网络架构以及所有节点的计算和通信容量。这基本上涉及两个高耦合程序:模型生成和模型分裂。在本文中,提出了一种联合模型分割和神经结构搜索(JMSNAS)框架以在移动边缘网络上自动生成和部署DNN模型。考虑到计算和通信资源约束,配制计算图形搜索问题以查找DNN模型的多分裂点,然后培训模型以满足一些精度要求。此外,通过正确设计目标函数来实现模型精度和完成延迟之间的权衡。实验结果证实了通过最先进的分机学习设计方法的提出框架的优越性。
translated by 谷歌翻译