Recent advancements in deep neural networks for graph-structured data have led to state-of-the-art performance on recommender system benchmarks. However, making these methods practical and scalable to web-scale recommendation tasks with billions of items and hundreds of millions of users remains a challenge.Here we describe a large-scale deep recommendation engine that we developed and deployed at Pinterest. We develop a dataefficient Graph Convolutional Network (GCN) algorithm PinSage, which combines efficient random walks and graph convolutions to generate embeddings of nodes (i.e., items) that incorporate both graph structure as well as node feature information. Compared to prior GCN approaches, we develop a novel method based on highly efficient random walks to structure the convolutions and design a novel training strategy that relies on harder-and-harder training examples to improve robustness and convergence of the model.We deploy PinSage at Pinterest and train it on 7.5 billion examples on a graph with 3 billion nodes representing pins and boards, and 18 billion edges. According to offline metrics, user studies and A/B tests, PinSage generates higher-quality recommendations than comparable deep learning and graph-based alternatives. To our knowledge, this is the largest application of deep graph embeddings to date and paves the way for a new generation of web-scale recommender systems based on graph convolutional architectures.
translated by 谷歌翻译
A primary objective of news articles is to establish the factual record for an event, frequently achieved by conveying both the details of the specified event (i.e., the 5 Ws; Who, What, Where, When and Why regarding the event) and how people reacted to it (i.e., reported statements). However, existing work on news summarization almost exclusively focuses on the event details. In this work, we propose the novel task of summarizing the reactions of different speakers, as expressed by their reported statements, to a given event. To this end, we create a new multi-document summarization benchmark, SUMREN, comprising 745 summaries of reported statements from various public figures obtained from 633 news articles discussing 132 events. We propose an automatic silver training data generation approach for our task, which helps smaller models like BART achieve GPT-3 level performance on this task. Finally, we introduce a pipeline-based framework for summarizing reported speech, which we empirically show to generate summaries that are more abstractive and factual than baseline query-focused summarization approaches.
translated by 谷歌翻译
面向目标的生成脚本学习旨在根据目标生成后续步骤,这是帮助机器人进行日常生活的刻板印象活动的重要任务。我们表明,如果历史状态不仅被给人的语言指示捕获,而且还可以增强随附图像提供的其他信息,可以提高此任务的性能。因此,我们提出了一项新任务,多媒体生成脚本学习,以通过跟踪文本和视觉方式中的历史状态,并介绍包含2,338个任务和31,496个步骤的第一个基准,从而生成后续步骤。我们旨在生成视觉状态的脚本,这些脚本是可跟踪的,对看不见的任务的诱导性,并且在各自的步骤中多样化。我们建议通过多媒体选择性编码器编码视觉状态更改,并使用检索仪的解码器从先前观察到的任务中转移知识,并通过优化面向多样性的对比度学习目标来在每个步骤中介绍不同的信息。我们定义指标以评估发电质量和电感质量。实验结果表明,我们的方法明显优于强质基线。
translated by 谷歌翻译
对抗性培训(AT)被认为是对抗对抗攻击最可靠的防御之一。然而,模型培训以牺牲标准精度,并不概括为新的攻击。最近的作用表明,在新型威胁模型中的新威胁模型或神经感知威胁模型中,对普遍威胁模型的对抗样本进行了泛化改进。然而,前者需要确切的流形信息,而后者需要算法放松。通过这些考虑因素,我们利用了具有规范化流的底层歧管信息,确保了确切的歧管的假设保持。此外,我们提出了一种名为联合空间威胁模型(JSTM)的新型威胁模型,其可以作为神经感知威胁模型的特殊情况,这些威胁模型不需要额外放松来制作相应的对抗性攻击。在JSTM下,我们培养了新的对抗性攻击和防御。混合策略提高了神经网络的标准准确性,但与AT结合时牺牲了鲁棒性。为了解决这个问题,我们提出了强大的混合策略,其中我们最大限度地提高了内插图像的逆境,并获得了鲁棒性和预装配。我们的实验表明,内插关节空间对抗性训练(IJSAT)在CiFar-10/100,Om-ImageNet和CiFar-10-C数据集中实现了标准精度,鲁棒性和泛化的良好性能。 IJSAT也是灵活的,可以用作数据增强方法,以提高标准精度,并与诸多换取以提高鲁棒性的方法相结合。
translated by 谷歌翻译
最近的研究表明,对对抗性攻击的鲁棒性可以跨网络转移。换句话说,在强大的教师模型的帮助下,我们可以使模型更加强大。我们问是否从静态教师那里学习,可以模特“学习”和“互相教导”来实现更好的稳健性?在本文中,我们研究模型之间的相互作用如何通过知识蒸馏来影响鲁棒性。我们提出了互联土训练(垫子),其中多种模型一起培训并分享对抗性示例的知识,以实现改善的鲁棒性。垫允许强大的模型来探索更大的对抗样本空间,并找到更强大的特征空间和决策边界。通过对CIFAR-10和CIFAR-100的广泛实验,我们证明垫可以在白盒攻击下有效地改善模型稳健性和最优异的现有方法,使$ \ SIM为8%的准确性增益对香草对抗培训(在PGD-100袭击下。此外,我们表明垫子还可以在不同的扰动类型中减轻鲁棒性权衡,从$ l_ \ infty $,$ l_2 $和$ l_1 $攻击中带来基线的基线。这些结果表明了该方法的优越性,并证明协作学习是设计强大模型的有效策略。
translated by 谷歌翻译
对象检测在许多安全关键系统中播放关键作用。对抗性补丁攻击,在物理世界中易于实施,对最先进的对象探测器构成严重威胁。开发针对补丁攻击的对象探测器的可靠防御是至关重要的,但严重解读。在本文中,我们提出了段和完整的防御(SAC),是通过检测和消除对抗性补丁来保护对象探测器的一般框架。我们首先培训一个补丁分段器,输出补丁掩码,提供对抗性补丁的像素级定位。然后,我们提出了一种自我逆势训练算法来强制补丁分段器。此外,我们设计了一种坚固的形状完成算法,保证了给定贴片分段器的输出在地面真理贴片掩模的某个汉明距离的图像中从图像中移除整个修补程序。我们对Coco和Xview Datasets的实验表明,即使在具有清洁图像上没有性能下降的强大自适应攻击下,SAC也可以实现优越的稳健性,并且概括到未遵守的补丁形状,攻击预算和看不见的攻击方法。此外,我们介绍了股份模型数据集,该数据集增强了具有对抗修补程序的像素级注释的杏子数据集。我们展示SAC可以显着降低物理补丁攻击的目标攻击成功率。
translated by 谷歌翻译
在过去十年中,发光二极管(LED)几乎在每个应用中都取代了常见的灯泡,从智能手机中的手电筒到汽车前灯。照亮夜间街道需要LED发出光谱,被人眼被人眼被视为纯白色。与这种白光谱相关的电力不仅分布在贡献波长上,而且在视觉角度上分布。对于许多应用,可用的光线需要在向前的方向上退出LED,即在小角度到垂直。在这项工作中,我们证明了白色LED顶部的专门设计的多层薄膜增加了向前发射的纯白光的功率。因此,推导的多目标优化问题是通过实质物理引导的目标函数重新重新制定,该函数代表了我们工程问题的层次结构。采用贝叶斯优化的变体基于射线跟踪模拟来最大化这种非确定性目标函数。最终,对合适的多层薄膜的光学性质的研究允许识别白光方向性的增加的机制:角度和波长选择性过滤导致多层薄膜与光线的乒乓球发挥作用。
translated by 谷歌翻译
元强化学习(RL)方法可以使用比标准RL少的数据级的元培训策略,但元培训本身既昂贵又耗时。如果我们可以在离线数据上进行元训练,那么我们可以重复使用相同的静态数据集,该数据集将一次标记为不同任务的奖励,以在元测试时间适应各种新任务的元训练策略。尽管此功能将使Meta-RL成为现实使用的实用工具,但离线META-RL提出了除在线META-RL或标准离线RL设置之外的其他挑战。 Meta-RL学习了一种探索策略,该策略收集了用于适应的数据,并元培训策略迅速适应了新任务的数据。由于该策略是在固定的离线数据集上进行了元训练的,因此当适应学识渊博的勘探策略收集的数据时,它可能表现得不可预测,这与离线数据有系统地不同,从而导致分布变化。我们提出了一种混合脱机元元素算法,该算法使用带有奖励的脱机数据来进行自适应策略,然后收集其他无监督的在线数据,而无需任何奖励标签来桥接这一分配变化。通过不需要在线收集的奖励标签,此数据可以便宜得多。我们将我们的方法比较了在模拟机器人的运动和操纵任务上进行离线元rl的先前工作,并发现使用其他无监督的在线数据收集可以显着提高元训练政策的自适应能力,从而匹配完全在线的表现。在一系列具有挑战性的域上,需要对新任务进行概括。
translated by 谷歌翻译
While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the task, but also provide sufficient shaping to accomplish it. In this paper, we view reinforcement learning as inferring policies that achieve desired outcomes, rather than as a problem of maximizing rewards. To solve this inference problem, we establish a novel variational inference formulation that allows us to derive a well-shaped reward function which can be learned directly from environment interactions. From the corresponding variational objective, we also derive a new probabilistic Bellman backup operator and use it to develop an off-policy algorithm to solve goal-directed tasks. We empirically demonstrate that this method eliminates the need to hand-craft reward functions for a suite of diverse manipulation and locomotion tasks and leads to effective goal-directed behaviors.
translated by 谷歌翻译
This paper studies the unsupervised embedding learning problem, which requires an effective similarity measurement between samples in low-dimensional embedding space. Motivated by the positive concentrated and negative separated properties observed from category-wise supervised learning, we propose to utilize the instance-wise supervision to approximate these properties, which aims at learning data augmentation invariant and instance spreadout features. To achieve this goal, we propose a novel instance based softmax embedding method, which directly optimizes the 'real' instance features on top of the softmax function. It achieves significantly faster learning speed and higher accuracy than all existing methods. The proposed method performs well for both seen and unseen testing categories with cosine similarity. It also achieves competitive performance even without pre-trained network over samples from fine-grained categories.
translated by 谷歌翻译