Update！H5支撑摘要折叠，体会更佳！点击拜访arxivdaily.com
cs.LG 方向，今天合计70篇
Graph相关(图学习|图神经网络|图优化等)(4篇)
【1】 Structure-Aware Hard Negative Mining for Heterogeneous Graph Contrastive Learning
标题：根据结构感知的异构图比照学习硬否定发掘
链接：https://arxiv.org/abs/2108.13886
组织：Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, School of Artificial Intelligence, University of Chinese Academy of Sciences
补白
摘要
摘要
【2】 Heterogeneous Graph Neural Network with Multi-view Representation Learning
标题：具有多视图标明学习的异构图神经网络
链接：https://arxiv.org/abs/2108.13650
组织： HuazhongUniversity of Science and Technology
摘要：异构图嵌入的图神经网络是经过探究异构图的异构性和语义，将节点投影到低维空间。可是，一方面，现有的大多数异构图嵌入办法要么对特定语义下的部分结构建模缺乏，要么在聚合信息时疏忽了异构性。另一方面，来自多个语义的标明没有全面集成以取得通用的节点嵌入。为了处理这个问题，咱们引进多视图标明学习的思维，提出了一种根据多视图标明学习的异构图神经网络（MV-HetGNN），用于异构图的嵌入。该模型包含节点特征转化、视图特定的自我图编码和自动多视图交融，以完全学习杂乱的结构和语义信息，生成全面的节点标明。在三个实在的异构图形数据集上进行的很多试验标明，所提出的MV-HetGNN模型在各种下流使命（例如节点分类、节点聚类和链路猜测）中一直优于一切最早进的GNN基线。
摘要：Graph neural networks for heterogeneous graph embedding is to project nodes
into a low-dimensional space by exploring the heterogeneity and semantics of
the heterogeneous graph. However, on the one hand, most of existing
heterogeneous graph embedding methods either insufficiently model the local
structure under specific semantic, or neglect the heterogeneity when
aggregating information from it. On the other hand, representations from
multiple semantics are not comprehensively integrated to obtain versatile node
embeddings. To address the problem, we propose a Heterogeneous Graph Neural
Network with Multi-View Representation Learning (named MV-HetGNN) for
heterogeneous graph embedding by introducing the idea of multi-view
representation learning. The proposed model consists of node feature
transformation, view-specific ego graph encoding and auto multi-view fusion to
thoroughly learn complex structural and semantic information for generating
comprehensive node representations. Extensive experiments on three real-world
heterogeneous graph datasets show that the proposed MV-HetGNN model
consistently outperforms all the state-of-the-art GNN baselines in various
downstream tasks, e.g., node classification, node clustering, and link
prediction.
【3】 Adaptive Label Smoothing To Regularize Large-Scale Graph Training
标题：自适应标签滑润在规则化大规模图练习中的运用
链接：https://arxiv.org/abs/2108.13555
组织：Rice University, University of Georgia, Samsung Research America, Samsung Electronics
摘要
摘要
标题：一种鸿沟有向图嵌入法的有限元署理模型
链接：https://arxiv.org/abs/2108.13509
组织：Aggarwalb, School of Mechanical Engineering, Purdue University, Purdue Mall, West Lafayette, IN , USA, School of Industrial Engineering, Purdue University, Purdue Mall, West Lafayette, IN , USA
摘要：在这项作业中，咱们提出了一种面向鸿沟的图嵌入（BOGE）办法，用于图神经网络（GNN）作为回归物理场和求解边值问题的通用代替模型。BOGE办法为鸿沟元素和部分相邻元素供给快捷办法，能够将结构化网格元素嵌入到图形中，并对根据大规模三角形网格的FEA成果履行有用回归，这是其他根据机器学习的署理办法无法完成的。针对悬臂梁问题，咱们的BOGE办法不仅能拟合应力场散布，而且能回归拓扑优化成果，显现了其完成笼统决议计划规划进程的潜力。选用三层DeepGCN模型的BOGE办法完成了应力场猜测的MSE为0.011706（2.41\%MAPE）和拓扑优化的MSE为0.002735（1.58\%元素的差错大于0.01）的回归。}BOGE办法的整体概念为通用和高效的根据深度学习的FEA模仿器，将对工业和规划相关范畴都有利。
摘要
Transformer(1篇)
【1】 Medical SANSformers: Training self-supervised transformers without attention for Electronic Medical Records
标题
链接：https://arxiv.org/abs/2108.13672
组织：Department of Computer Science, Aalto University, Finland, Information Services Department, Finnish Institute for Health and Welfare, Finland, Department of Mathematics and Statistics, University of Helsinki, Finland, Editor:
补白：25 pages, 8 figures, 5 tables, Submitted to a journal
摘要
摘要
GAN|对立|进犯|生成相关(8篇)
【1】 Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study
标题：用于有用推理的生成性对立网络的量化：办法论研讨
链接：https://arxiv.org/abs/2108.13996
组织：Higher School of Economics, Skolkovo Institute of Science and Technology, Samsung AI Center Moscow, Moscow, Russia, Yandex, Samsung-HSE Laboratory
摘要
摘要
【2】 Morphence: Moving Target Defense Against Adversarial Examples
标题：Morphence：针对敌方的移动方针防护示例
链接：https://arxiv.org/abs/2108.13952
组织：University of Michigan, Dearborn
补白：None
摘要：对机器学习模型的对立性示例的鲁棒性依然是一个敞开的研讨主题。进犯一般是经过重复勘探固定方针模型，并成心制造对立性示例来捉弄它而成功的。在本文中，咱们介绍了变形，这是一种经过使模型成为对立对手的移动方针来改动防护格式的办法。经过定时移动模型的决议计划函数，Morphence使重复或相关进犯的成功变得十分困难。Morphence以一种在呼应猜测查询时引进满足随机性的办法布置从根底模型生成的模型池。为保证重复进犯或相关进犯失利，在到达查询预算后，布置的模型池将自动过期，而且模型池将无缝替换为预先生成的新模型池。咱们在两个基准图画分类数据集（MNIST和CIFAR10）上评价了五种参阅进犯（2种白盒和3种黑盒）下的变形。在一切状况下，Morphence一直优于迄今为止有用的防护和对立性练习，即便在面临强壮的白盒进犯时也是如此，一起保存了洁净数据的精确性。
摘要
【3】 EG-Booster: Explanation-Guided Booster of ML Evasion Attacks
标题：EG-Booster：解说制导的ML躲避进犯助推器
链接：https://arxiv.org/abs/2108.13930
组织：University of Michigan, Dearborn
摘要：机器学习（ML）在很多范畴的广泛运用，使人们对其在安全要害环境中的可信性发生了疑问。寻求可信ML的一部分是对ML模型进行健壮性评价，以测验时刻对立性示例。与可信的ML方针相一致，根据特征的模型猜测解说或许有助于健壮性评价。在本文中，咱们提出了一种称为EG-Booster的新办法，该办法运用可解说ML中的技能来辅导对立性示例制造，以改善ML模型的健壮性评价，然后再将其布置到安全要害环境中。EG-Booster中的要害洞悉是运用根据特征的模型猜测解说，经过增加或许导致模型躲避的后果性扰动和避免不或许导致躲避的非后果性扰动来辅导对立性示例制造。EG-Booster对模型架构、要挟模型不可知，并支撑曾经文献中运用的各种间隔衡量。咱们运用图画分类基准数据集MNIST和CIFAR10评价EG-Booster。咱们的研讨成果标明，EG-Booster能够明显进步最早进进犯的躲避率，一起削减搅扰次数。经过掩盖四个白盒和三个黑盒进犯的广泛试验，咱们证明了EG-Booster对在MNIST和CIFAR10上练习的两个未设防神经网络以及在CIFAR10上练习的另一个经对立练习的ResNet模型的有用性。此外，咱们引进了一个稳定性评价方针，并经过调查模型在多个EG助推器运转期间的分类输出之间的相似性来评价咱们根据解说的办法的牢靠性。
摘要
【4】 Beyond Model Extraction: Imitation Attack for Black-Box NLP APIs
标题：逾越模型提取：黑盒NLP API的仿照进犯
链接：https://arxiv.org/abs/2108.13873
组织：The Australian National University, Canberra, ACT, Australia, Data, CSIRO, Canberra, ACT, Australia, Monash University, Clayton, VIC, Australia, Sony AI, Japan
摘要：机器学习即服务（MLaaS）现已招引了数以百万计的用户运用其功能优于杂乱的模型。虽然发布为黑盒API，但这些服务背面的有价值的模型依然简略遭到仿照进犯。最近，一系列研讨标明进犯者能够盗取或提取受害者模型。虽然如此，曾经被盗的模型中没有一个能比本来的黑盒API更好。在这项作业中，咱们迈出了第一步，证明进犯者能够经过无监督的域自适应和多受害者集成潜在地逾越受害者。在基准数据集和实在国际的API上进行的很多试验验证了仿照者能够成功地逾越原始的黑盒模型。咱们以为这是仿照进犯研讨的一个里程碑，特别是在NLP API上，因为优胜的功能会影响API供给者的防护乃至发布战略。
摘要：Machine-learning-as-a-service (MLaaS) has attracted millions of users to
their outperforming sophisticated models. Although published as black-box APIs,
the valuable models behind these services are still vulnerable to imitation
attacks. Recently, a series of works have demonstrated that attackers manage to
steal or extract the victim models. Nonetheless, none of the previous stolen
models can outperform the original black-box APIs. In this work, we take the
first step of showing that attackers could potentially surpass victims via
unsupervised domain adaptation and multi-victim ensemble. Extensive experiments
on benchmark datasets and real-world APIs validate that the imitators can
succeed in outperforming the original black-box models. We consider this as a
milestone in the research of imitation attack, especially on NLP APIs, as the
superior performance could influence the defense or even publishing strategy of
API providers.
【5】 Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models
标题：根据强化学习的视频辨认模型稀少黑盒对立进犯
链接：https://arxiv.org/abs/2108.13872
组织：Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University
补白：None
摘要：咱们探讨了视频辨认模型上的黑盒对立进犯。进犯仅在选定的要害区域和要害帧上履行，以下降因视频高维性而查找对立性搅扰的高核算本钱。要挑选要害帧，一种办法是运用启发式算法评价每个帧的重要性并挑选要害帧。可是，它在排序和查找方面的时刻功率很低。为了加快进犯进程，咱们提出了一种根据强化学习的帧挑选战略。详细来说，署理探究原始类和方针类视频之间的差异，以做出挑选决议计划。它从显现决议计划质量的要挟模型中取得奖赏。此外，咱们还运用明显性检测来挑选要害区域，并在零阶优化中仅估量梯度符号，而不是梯度自身，以进一步进步进犯进程。咱们能够在非方针进犯中直接运用经过练习的模型，也能够在方针进犯中进行少数微调，然后节约核算时刻。对实在数据集的一系列实证成果标明了该办法的有用性和有用性。
摘要：We explore the black-box adversarial attack on video recognition models.
Attacks are only performed on selected key regions and key frames to reduce the
high computation cost of searching adversarial perturbations on a video due to
its high dimensionality. To select key frames, one way is to use heuristic
algorithms to evaluate the importance of each frame and choose the essential
ones. However, it is time inefficient on sorting and searching. In order to
speed up the attack process, we propose a reinforcement learning based frame
selection strategy. Specifically, the agent explores the difference between the
original class and the target class of videos to make selection decisions. It
receives rewards from threat models which indicate the quality of the
decisions. Besides, we also use saliency detection to select key regions and
only estimate the sign of gradient instead of the gradient itself in zeroth
order optimization to further boost the attack process. We can use the trained
model directly in the untargeted attack or with little fine-tune in the
targeted attack, which saves computation time. A range of empirical results on
real datasets demonstrate the effectiveness and efficiency of the proposed
method.
【6】 Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings
标题：根据自监督嵌入的对立性进犯样本高效检测与分类
链接：https://arxiv.org/abs/2108.13797
组织：Department of Computer Science, University of Maryland
补白：Accepted to ICCV 2021
摘要：深部模型的对立性健壮性关于保证在实在环境中的安全布置至关重要，但大多数现代防护规模狭隘，本钱贵重。在本文中，咱们提出了一种自监督的办法来检测对立性进犯，并将其分类到各自的要挟模型中，该办法根据一个线性模型，该模型根据预先练习的自监督编码器的嵌入操作。咱们在试验中运用了SimCLR编码器，因为咱们标明SimCLR嵌入间隔是人类感知才能的一个很好的署理，使其能够一起封装许多要挟模型。咱们称咱们的办法为SimCat，因为它运用SimCLR编码器捕获并分类各种类型的对立性进犯，包含L_p和非L_p躲避进犯，以及数据中毒。线性分类器的简略性质使得咱们的办法在时刻和样本杂乱度上都是有用的。例如，在SVHN上，仅运用PGD-L_inf进犯核算的五对洁净和对立性示例，SimCat的检测精度逾越85%。此外，在ImageNet上，仅运用每个要挟模型中的25个示例，SimCat就能够对八种不同的进犯类型进行分类，如PGD-L_2、PGD-L_inf、CW-L_2、PPGD、LPA、StAdv、RECLOR和JPEG-L_inf，精确率逾越40%。在STL10数据上，咱们运用SimCat作为对中毒进犯的防护，例如BP、CP、FC、CLBD、HTBD，在只运用20种总毒药进行练习的状况下，成功率下降了一半。咱们发现，检测器能够很好地推行到看不见的要挟模型。最终，咱们研讨了咱们的检测办法在自适应进犯下的功能，并经过对立性练习进一步增强了其对此类进犯的鲁棒性。
摘要
【7】 Segmentation Fault: A Cheap Defense Against Adversarial Machine Learning
标题：切割过错：对立对立性机器学习的廉价防护
链接：https://arxiv.org/abs/2108.13617
组织：American University of Beirut (AUB), Beirut, Lebanon, University of New Haven, West Haven, CT, USA
摘要：最近宣布的针对深层神经网络（DNN）的进犯强调了评价在要害体系中运用该技能的安全危险的办法和东西的重要性。检测对立性机器学习的有用技能有助于树立信赖，并促进在灵敏和安全体系中选用深度学习。在本文中，咱们提出了一种新的技能来维护深度神经网络分类器，特别是卷积分类器。咱们的防护是廉价的，因为它需求更少的核算才能，虽然在检测精度方面花费很小。这项作业引用了最近宣布的一种称为ML-LOO的技能。咱们选用粗粒度的漏选办法，替代了ML-LOO中贵重的逐像素漏选办法。咱们评价和比较了不同切割算法在这项使命中的功率。咱们的成果标明，即便检测精度略有下降，功率仍有或许大幅度进步。
摘要
【8】 How Does Adversarial Fine-Tuning Benefit BERT?
标题：对立性微调对BERT有什么优点？
链接：https://arxiv.org/abs/2108.13602
组织：Visa Research, Palo Alto, USA
摘要：对立性练习（AT）是机器学习中防护对立性进犯最牢靠的办法之一。该办法的变体已被用作正则化机制，以在NLP基准上完成SOTA成果，并被发现对搬迁学习和继续学习有用。咱们经过比照一般和晦气微调的BERT模型来寻觅AT有用性的原因。咱们以为在微调进程中部分保存BERT的句法才能是AT成功的要害。咱们调查到，逆向微调模型更忠诚于BERT的言语建模行为，而且对词序更灵敏。作为句法才能的详细比如，逆向微调模型在回指一致性方面的优势高达38%，在依赖性剖析方面的优势高达11%。咱们的剖析标明，香草精调过度简化了语句表达，首要会集在一个或几个标签指示词上。可是，AT缓和了这些有影响力的词语的影响，并鼓舞了代表性的多样性。这使得一个语句的表达愈加层次化，然后减轻了BERT的句法才能丢失。
摘要：Adversarial training (AT) is one of the most reliable methods for defending
against adversarial attacks in machine learning. Variants of this method have
been used as regularization mechanisms to achieve SOTA results on NLP
benchmarks, and they have been found to be useful for transfer learning and
continual learning. We search for the reasons for the effectiveness of AT by
contrasting vanilla and adversarially fine-tuned BERT models. We identify
partial preservation of BERT's syntactic abilities during fine-tuning as the
key to the success of AT. We observe that adversarially fine-tuned models
remain more faithful to BERT's language modeling behavior and are more
sensitive to the word order. As concrete examples of syntactic abilities, an
adversarially fine-tuned model could have an advantage of up to 38% on anaphora
agreement and up to 11% on dependency parsing. Our analysis demonstrates that
vanilla fine-tuning oversimplifies the sentence representation by focusing
heavily on one or a few label-indicative words. AT, however, moderates the
effect of these influential words and encourages representational diversity.
This allows for a more hierarchical representation of a sentence and leads to
the mitigation of BERT's loss of syntactic abilities.
半/弱/无/有监督|不确定性|自动学习(3篇)
【1】 S4-Crowd: Semi-Supervised Learning with Self-Supervised Regularisation for Crowd Counting
标题
链接：https://arxiv.org/abs/2108.13969
组织：Newcastle University
摘要
摘要
【2】 Self-balanced Learning For Domain Generalization
标题：自平衡学习在范畴泛化中的运用
链接：https://arxiv.org/abs/2108.13597
组织：†School of Electrical and Electronic Engineering, Yonsei University, Seoul, Korea, ‡Department of Computer Science and Engineering, Ewha Womans University, Seoul, Korea
补白：None
摘要：范畴泛化的意图是在多范畴源数据上学习一个猜测模型，使该模型能够泛化到具有不知道核算信息的方针范畴。大多数现有办法都是在假定源数据在域和类方面都很平衡的状况下开发的。可是，运用不同组合差错搜集的实在国际练习数据往往在范畴和类别上表现出严峻的散布距离，导致功能大幅下降。在本文中，咱们提出了一个自平衡的范畴泛化结构，该结构自适应地学习丢失的权重，以减轻由多范畴源数据的不同散布所引起的差错。自平衡计划根据一个辅佐从头加权网络，该网络经过运用平衡元数据迭代更新以域和类信息为条件的丢失权重。试验成果标明，咱们的办法在范畴泛化方面是有用的。
摘要
【3】 Semi-Supervised Exaggeration Detection of Health Science Press Releases
标题：卫生科学新闻稿的半监督夸大检测
链接：https://arxiv.org/abs/2108.13493
组织：Dept. of Computer Science, University of Copenhagen, Denmark
补白：Accepted to EMNLP 2021; 13 pages, 6 figures, 9 tables
摘要：群众对科学的信赖有赖于科学论文的诚笃和脚踏实地的沟通。可是，最近的研讨标明，新闻媒体倾向于经过夸大科学论文的发现来曲解科学论文。有鉴于此，咱们提出了一个形式化的和研讨的问题，夸大检测在科学传达。虽然有很多关于它们的科学论文和群众媒体文章，但这些文章很少直接链接到原始论文，这使得数据搜集具有应战性。咱们经过策划一组有标签的新闻稿/摘要对来处理这一问题，这些新闻稿/摘要对来自现有的专家注释研讨，这些研讨是关于科学论文新闻稿中的夸大现象，适用于对使命中机器学习模型的功能进行基准测验。运用本研讨和从前科学中夸大检测研讨的有限数据，咱们介绍了MT-PET，一种形式运用练习（PET）的多使命版别，它运用互补完形填空式QA使命的常识来改善Few-Shot学习。咱们证明，无论是在数据有限的状况下，仍是在主使命数据丰厚的状况下，MT-PET都优于PET和监督学习。
摘要：Public trust in science depends on honest and factual communication of
scientific papers. However, recent studies have demonstrated a tendency of news
media to misrepresent scientific papers by exaggerating their findings. Given
this, we present a formalization of and study into the problem of exaggeration
detection in science communication. While there are an abundance of scientific
papers and popular media articles written about them, very rarely do the
articles include a direct link to the original paper, making data collection
challenging. We address this by curating a set of labeled press
release/abstract pairs from existing expert annotated studies on exaggeration
in press releases of scientific papers suitable for benchmarking the
performance of machine learning models on the task. Using limited data from
this and previous studies on exaggeration detection in science, we introduce
MT-PET, a multi-task version of Pattern Exploiting Training (PET), which
leverages knowledge from complementary cloze-style QA tasks to improve few-shot
learning. We demonstrate that MT-PET outperforms PET and supervised learning
both when data is limited, as well as when there is an abundance of data for
the main task.
搬迁|Zero/Few/One-Shot|自适应(2篇)
【1】 Aligning Hotel Embeddings using Domain Adaptation for Next-Item Recommendation
标题：运用用于下一项引荐的范畴适配来对齐酒店嵌入
链接：https://arxiv.org/abs/2108.13824
组织：Expedia Group, Geneva, Switzerland
补白：ACM SIGIR Workshop on eCommerce, July 15, 2021, Virtual Event, Montreal, Canada
摘要
摘要：In online platforms it is often the case to have multiple brands under the
same group which may target different customer profiles, or have different
domains. For example, in the hospitality domain, Expedia Group has multiple
brands like Brand Expedia, Hotels.com and Wotif which have either different
traveler profiles or are more relevant in a local context.
In this context, learning embeddings for hotels that can be leveraged in
recommendation tasks in multiple brands requires to have a common embedding
that can be induced using alignment approaches. In the same time, one needs to
ensure that this common embedding space does not degrade the performance in any
of the brands.
In this work we build upon the hotel2vec model and propose a simple
regularization approach for aligning hotel embeddings of different brands via
domain adaptation. We also explore alignment methods previously used in
cross-lingual embeddings to align spaces of different languages. We present
results on the task of next-hotel prediction using click sessions from two
brands. The results show that the proposed approach can align the two embedding
spaces while achieving good performance in both brands. Additionally, with
respect to single-brand training we show that the proposed approach can
significantly reduce training time and improve the predictive performance.
【2】 Rapidly and accurately estimating brain strain and strain rate across head impact types with transfer learning and data fusion
标题：运用搬运学习和数据交融快速精确地估量不同头部碰击类型的脑应变和应变率
链接：https://arxiv.org/abs/2108.13577
组织： Gevaert is with the Department of Biomedical Data Science and StanfordCenter for Biomedical Informatics Research, Stanford University
补白：14 pages, 6 figures
摘要：脑应变和应变率可有用猜测头部碰击形成的创伤性脑损伤（TBI）。可是，先进的有限元建模（FEM）在核算中需求很多的核算时刻，约束了其在实时TBI危险监测中的运用。为了加快速度，开发了机器学习头部模型（MLHMs），发现当练习/测验数据集来自不同的头部磕碰类型时，模型精度下降。可是，特定影响类型的数据集巨细或许缺乏以进行模型练习。为了处理有限元法的核算本钱、有限应变率猜测以及MLHMs对现场数据集的可推行性，咱们提出了数据交融和搬运学习来开发一系列猜测最大主应变（MPS）和最大主应变率（MPSR）的MLHMs。咱们对来自模仿、美式足球、混合功夫、事故的13623次头部磕碰的MLHMs进行了练习和测验，并与仅在模仿或仅在现场磕碰中练习的模型进行了比较。运用搬运学习开发的MLHMs在预算MPS和MPSR方面比其他模型更精确，在猜测MPS方面的均匀肯定差错（MAE）小于0.03，在猜测一切影响数据集的MPSR方面的均匀肯定差错（MAE）小于7（1/s）。MLHMs可运用于各种头部磕碰类型，以快速精确地核算大脑应变和应变率。除了在实时脑应变和应变率监测中的临床运用外，该模型有助于研讨人员比FEM更有用地估量头部碰击引起的脑应变和应变率。
摘要
强化学习(2篇)
【1】 WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU
标题：WarpDrive：GPU上极快的端到端深度多Agent强化学习
链接：https://arxiv.org/abs/2108.13976
组织：Salesforce Research
补白：TL and SS contributed equally. Code is available at this https URL 14 pages, 7 figures
摘要：深度强化学习（RL）是在杂乱动态环境中练习决议计划模型的强壮结构。可是，当RL经过与环境模仿的重复交互进行学习时，它或许会变慢。加快RL需求算法和工程立异。特别是，在以多个署理或高维状况、调查或动作空间为特征的杂乱环境中运用RL时，存在要害的体系工程瓶颈。咱们介绍了WarpDrive，这是一个灵敏、轻量级、易于运用的开源RL结构，它根据PyCUDA和PyTorch，在单个GPU（图形处理单元）上完成端到端多署理RL。与混合CPU模仿和GPU模型的常见完成比较，WarpDrive运用GPU的极点并行才能，完成了数量级的快速RL。咱们的规划运转模仿，每个模仿中的署理并行运转。它消除了CPU和GPU之间的数据仿制。它还运用GPU上的单个模仿数据存储，该数据存储能够安全地就地更新。总归，这答运用户运转数千个并发多署理模仿，并对很多体会进行练习。例如，WarpDrive在基准测验符号模仿中每秒发生290万个环境进程，其中有2000个环境和1000个署理（与CPU完成比较，吞吐量至少高出100倍）。WarpDrive供给了一个轻量级Python接口和环境包装器，以简化运用并进步灵敏性和扩展性。因而，WarpDrive供给了构建高吞吐量RL体系的结构。
摘要
【2】 Identifying optimal cycles in quantum thermal machines with reinforcement-learning
标题：根据强化学习的量子热机最优循环辨认
链接：https://arxiv.org/abs/2108.13525
组织： † 1Freie Universit¨at Berlin, Department of Mathematics and Computer Science, Germany 2Freie Universit¨at Berlin, Department of Physics, Germany 3Rice University, Department of Chemistry
补白：14 pages, 7 figures
摘要：敞开量子体系的最优操控是一项具有应战性的使命，但在改善现有量子信息处理技能方面具有要害作用。咱们介绍了一个根据强化学习的通用结构，以发现最佳热力学循环，最大极限地进步非平衡量子热机和冰箱的功率。咱们将咱们的办法运用于三个体系：一个基准两级体系热机，在这里咱们找到了最佳已知循环；一个根据超导量子位发生相干的试验实在冰箱，咱们发现一个非直观的操控序列优于文献中提出的从前周期；一个根据量子谐振子的热机，咱们发现一个结构杂乱的循环比优化的奥托循环好。然后，咱们在最大功率下评价相应的功率。
摘要
医学相关(3篇)
【1】 Clustering of Pain Dynamics in Sickle Cell Disease from Sparse, Uneven Samples
标题：来自稀少、不均匀样本的镰刀细胞病痛苦动力学的聚类
链接：https://arxiv.org/abs/2108.13963
组织：∗Engineering Science and Applied Mathematics, Northwestern University, Evanston, IL, USA, †Computer Science and Engineering, Wright State University, Dayton, OH, USA, ‡Department of Medicine, Duke University, Durham, NC, USA
补白：7 pages, 5 figures
摘要：不规则采样的时刻序列数据在许多范畴都很常见。在这种状况下，许多从数据中提取洞悉力的典型办法都失利了。在这里，咱们企图将聚类轨道的办法推行到不规则和稀少采样数据。咱们首要构建组成数据集，然后提出并评价四种数据对齐办法，以便运用光谱聚类。咱们还对镰状细胞病患者的医疗记载中提取的实在数据重复相同的进程，这些患者的片面痛苦体会经过移动运用程序盯梢了几个月。咱们发现，对齐不规则采样稀少数据集的不同办法能够导致不同的最优聚类数，即便关于具有已知特点的组成数据也是如此。关于镰状细胞病的病例，咱们发现三组是一个合理的挑选，它们好像对应于（1）偶然出现急性痛苦的低痛组，（2）阅历一般从低到高动摇的中度均匀痛苦的组，以及（3）阅历继续高水平痛苦的组。咱们的研讨成果或许有助于医师和患者更好地了解和办理患者的痛苦程度，咱们期望咱们开发的办法将运用于医学和其他范畴的广泛数据源。
摘要：Irregularly sampled time series data are common in a variety of fields. Many
typical methods for drawing insight from data fail in this case. Here we
attempt to generalize methods for clustering trajectories to irregularly and
sparsely sampled data. We first construct synthetic data sets, then propose and
assess four methods of data alignment to allow for application of spectral
clustering. We also repeat the same process for real data drawn from medical
records of patients with sickle cell disease -- patients whose subjective
experiences of pain were tracked for several months via a mobile app.
We find that different methods for aligning irregularly sampled sparse data
sets can lead to different optimal numbers of clusters, even for synthetic data
with known properties. For the case of sickle cell disease, we find that three
clusters is a reasonable choice, and these appear to correspond to (1) a low
pain group with occasionally acute pain, (2) a group which experiences moderate
mean pain that fluctuates often from low to high, and (3) a group that
experiences persistent high levels of pain.
Our results may help physicians and patients better understand and manage
patients' pain levels over time, and we expect that the methods we develop will
apply to a wide range of other data sources in medicine and beyond.
【2】 Modeling the effect of the vaccination campaign on the Covid-19 pandemic
标题：模仿疫苗接种运动对冠状病毒大盛行的影响
链接：https://arxiv.org/abs/2108.13908
组织：John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts , Department of Physics, Harvard University, Cambridge, Massachusetts , USA
摘要
摘要：Population-wide vaccination is critical for containing the SARS-CoV-2
(Covid-19) pandemic when combined with restrictive and prevention measures. In
this study, we introduce SAIVR, a mathematical model able to forecast the
Covid-19 epidemic evolution during the vaccination campaign. SAIVR extends the
widely used Susceptible-Infectious-Removed (SIR) model by considering the
Asymptomatic (A) and Vaccinated (V) compartments. The model contains several
parameters and initial conditions that are estimated by employing a
semi-supervised machine learning procedure. After training an unsupervised
neural network to solve the SAIVR differential equations, a supervised
framework then estimates the optimal conditions and parameters that best fit
recent infectious curves of 27 countries. Instructed by these results, we
performed an extensive study on the temporal evolution of the pandemic under
varying values of roll-out daily rates, vaccine efficacy, and a broad range of
societal vaccine hesitancy/denial levels. The concept of herd immunity is
questioned by studying future scenarios which involve different vaccination
efforts and more infectious Covid-19 variants.
【3】 Temporal Deep Learning Architecture for Prediction of COVID-19 Cases in India
标题：用于猜测印度冠状病毒病例的时刻深度学习结构
链接：https://arxiv.org/abs/2108.13823
组织：Bareilly College, Bareilly, Uttar Pradesh, India , School of Computational and Intergative Sciences, Jawaharlal Nehru University, New Delhi, India , CSIR-Central Electronics Engineering Research Institute,Pilani Rajasthan, India
补白：13 pages
摘要：为了对立最近的冠状病毒病2019（COVID-19），院士和临床医师正在寻觅新的办法来猜测COVID-19爆发的动态趋势，这或许减缓或阻挠大盛行。比如易感感染康复（SIR）及其变体等盛行病学模型有助于了解大盛行的动态趋势，可用于决议计划以优化流行症的或许操控。但这些根据数学假定的盛行病学模型或许无法猜测真实的大盛行状况。最近，2019冠状病毒疾病的动态趋势被用来了解新的机器学习办法。在本文中，咱们规划了递归和卷积神经网络模型：香草LSTM、堆叠LSTM、ED-LSTM、Bi LSTM、美国有线电视新闻网和混合美国有线电视新闻网+LSTM模型，以捕获COVID-19爆发的杂乱趋势，并对印度及其四个受影响最大的国家（马哈拉施特拉）进行7, 14, 21天的COVID-19日确诊病例的猜测，喀拉拉邦、卡纳塔克邦和泰米尔纳德邦）。在测验数据上核算均方根差错（RMSE）和均匀肯定百分比差错（MAPE）评价方针，以证明这些模型的相对功能。成果标明，与其他模型比较，叠加LSTM和CNN+LSTM混合模型的功能最好。
摘要
引荐(1篇)
【1】 Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations
标题：根据最大功效的次序查询引荐ARM挑选战略
链接：https://arxiv.org/abs/2108.13810
组织：University of Glasgow, Glasgow, UK, University of West Attica, Greece
摘要：咱们考虑在闭环交互式学习设置中的查询引荐问题，如在线信息搜集和探究性剖析。这个问题能够自然地运用多装备土匪（MAB）结构来建模，该结构具有可数个兵器。可数个臂的规范MAB算法首要挑选一组随机的候选臂，然后在下流的该候选集上运用规范MAB算法，例如UCB。咱们证明了这种挑选战略一般会导致更高的累积懊悔，为此，咱们提出了一种根据最大功效的挑选战略。咱们标明，在在线信息搜集等使命中，选用次序查询主张，查询序列彼此相关，经过挑选对当时履行的查询具有最大功效的查询，能够将潜在最优查询的数量削减到可办理的巨细。咱们运用最新的在线文献发现服务日志文件进行的试验成果标明，与最早进的基线算法比较，所提出的arm挑选战略明显进步了累积懊悔率以及常用的随机挑选战略，用于各种布景下的多装备土匪算法。咱们的数据模型和源代码可从~\url取得{https://anonymous.4open.science/r/0e5ad6b7-ac02-4577-9212-c9d505d3dbdb/}.
摘要
超分辨率|去噪|去模糊|去雾(2篇)
【1】 Super-Resolution Appearance Transfer for 4D Human Performances
标题：4D人体扮演的超分辨率外观传递
链接：https://arxiv.org/abs/2108.13739
组织：Centre for Vision, Speech and Signal Processing, University of Surrey, UK
摘要：从多角度视频中对人进行4D重建的一个常见问题是捕获的动态纹路外观的质量，这取决于相机分辨率和捕获体积。一般，要求对摄像机进行帧处理以捕获动态功能的体积（$50m^3$）导致人员仅占有视界的一小部分$$10%。即便运用超高清晰度4k视频收集，这也会导致以低于规范清晰度0.5k视频分辨率对人进行采样，然后导致低质量烘托。在本文中，咱们提出了一种处理计划，经过运用数字静物照相机（$8k$）从静态高分辨率外观捕捉设备进行超分辨率外观搬运，以小体积（$8m^3$）捕捉人物。提出了一种从高分辨率静态捕获到动态视频功能捕获的超分辨率外观转化管道，以生成超分辨率动态纹路。这处理了两个要害问题：不同摄像机体系之间的色彩映射；并运用学习到的模型进行动态纹路贴图超分辨率处理。比照评价标明，在出现具有超分辨率动态纹路外观的4D功能捕获方面，在定性和定量方面都有明显改善。所提出的办法再现了静态捕获的高分辨率细节，一起坚持捕获视频的外观动态。
摘要：A common problem in the 4D reconstruction of people from multi-view video is
the quality of the captured dynamic texture appearance which depends on both
the camera resolution and capture volume. Typically the requirement to frame
cameras to capture the volume of a dynamic performance ($50m^3$) results in
the person occupying only a small proportion $$ 10% of the field of view. Even
with ultra high-definition 4k video acquisition this results in sampling the
person at less-than standard definition 0.5k video resolution resulting in
low-quality rendering. In this paper we propose a solution to this problem
through super-resolution appearance transfer from a static high-resolution
appearance capture rig using digital stills cameras ($ 8k$) to capture the
person in a small volume ($8m^3$). A pipeline is proposed for super-resolution
appearance transfer from high-resolution static capture to dynamic video
performance capture to produce super-resolution dynamic textures. This
addresses two key problems: colour mapping between different camera systems;
and dynamic texture map super-resolution using a learnt model. Comparative
evaluation demonstrates a significant qualitative and quantitative improvement
in rendering the 4D performance capture with super-resolution dynamic texture
appearance. The proposed approach reproduces the high-resolution detail of the
static capture whilst maintaining the appearance dynamics of the captured
video.
【2】 Attention-based Multi-Reference Learning for Image Super-Resolution
标题：根据注意力的图画超分辨率多参阅学习
链接：https://arxiv.org/abs/2108.13697
组织：Centre for Vision, Speech and Signal Processing, University of Surrey, UK
摘要
摘要
点云|SLAM|雷达|激光|深度RGBD相关(1篇)
【1】 InSeGAN: A Generative Approach to Segmenting Identical Instances in Depth Images
标题：InSeGan：深度图画中切割相同实例的发生式办法
链接：https://arxiv.org/abs/2108.13865
组织：Gonc¸alo Dias Pais,, Mitsubishi Electric Research Labs (MERL), Cambridge, MA, Instituto Superior T´ecnico, University of Lisbon, Portugal
补白：Accepted at ICCV 2021
摘要
摘要
联邦学习|隐私维护|加密(2篇)
【1】 GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization
标题：GRP-FED：经过全球正规化个性化处理联合学习中的客户失衡问题
链接：https://arxiv.org/abs/2108.13858
组织： People’s Republic of China 3National Institute ofHealth Data Science, People’s Repub-lic of China 4Institute of Medical Technology, Health Science Cen-ter of Peking University
补白：(FL-ICML'21) International Workshop on Federated Learning for User Privacy and Data Confidentiality in Conjunction with ICML 2021
摘要：因为数据在实践中出现出长尾性，因而联邦学习（FL）在涣散的客户机上作为实践运用进行练习是一项应战。咱们提出了一种大局正则化个性化（GRP-FED）办法来处理数据不平衡问题，办法是为每个客户机考虑一个大局模型和多个部分模型。经过自适应聚合，大局模型公平地对待多个客户机，并缓解了大局长尾问题。每个本地模型都从本地数据中学习，并与其散布相一致，以便进行自定义。为了避免部分模型过度拟合，GRP-FED运用了一个对立性的鉴别器来调整学习到的全部分分特征。很多成果标明，咱们的GRP-FED在实践国际MIT-BIH和组成CIFAR-10数据集的全球和本地场景下都有所改善，完成了可比功能并处理了客户不平衡问题。
摘要
【2】 Unit-Modulus Wireless Federated Learning Via Penalty Alternating Minimization
标题：根据赏罚替换最小化的单位模无线联合学习
链接：https://arxiv.org/abs/2108.13669
组织：∗Department of Electrical and Electronic Engineering, Southern University of Science and Technology, China, ⋄Department of Computer Science and Engineering, Southern University of Science and Technology, China
补白：IEEE Global Communications Conference 2021. arXiv admin note: substantial text overlap with arXiv:2101.12051
摘要：无线联合学习（FL）是一种新式的机器学习范式，经过无线通讯从散布式数据集练习大局参数模型。提出了一种单位模无线FL（UMWFL）结构，该结构经过优化相移一起上传部分模型参数和核算大局模型参数。该结构避免了杂乱的基带信号处理，然后下降了通讯推迟和完本钱钱。推导了练习丢失界，提出了赏罚替换最小化（PAM）算法来最小化非凸非润滑丢失界。在Car-Learning-to-Act（CARLA）平台上的试验成果标明，与基准计划比较，选用PAM算法的UMWFL结构完成了更小的练习丢失和测验差错。
摘要：Wireless federated learning (FL) is an emerging machine learning paradigm
that trains a global parametric model from distributed datasets via wireless
communications. This paper proposes a unit-modulus wireless FL (UMWFL)
framework, which simultaneously uploads local model parameters and computes
global model parameters via optimized phase shifting. The proposed framework
avoids sophisticated baseband signal processing, leading to both low
communication delays and implementation costs. A training loss bound is derived
and a penalty alternating minimization (PAM) algorithm is proposed to minimize
the nonconvex nonsmooth loss bound. Experimental results in the Car Learning to
Act (CARLA) platform show that the proposed UMWFL framework with PAM algorithm
achieves smaller training losses and testing errors than those of the benchmark
scheme.
推理|剖析|了解|解说(5篇)
【1】 Explainable AI for engineering design: A unified approach of systems engineering and component-based deep learning
标题：用于工程规划的可解说人工智能：体系工程和根据组件的深度学习的一致办法
链接：https://arxiv.org/abs/2108.13836
补白：19 pages
摘要：由机器学习创立的数据驱动模型在规划和工程的一切范畴都具有重要意义。它们在协助决议计划者发明具有更好功能和可继续性的新式人工制品方面具有很大潜力。可是，这些模型的有限泛化和黑盒特性导致了有限的可解说性和可重用性
本文来自网络，不代表快递资讯网立场。转载请注明出处： http://www.llaiot.com/logistics-news/2799.html
