机器学习算法 - Py学习 Py学习 » 机器学习算法

 http://www.python88.com/forum/ml
 量化
 
 深度学习因子 月喜迎开门红
机器学习算法 量化
极市平台
 
深度学习图像分类任务中那些不得不看的 个tricks总结
机器学习算法 极市平台
 
 
 深度学习模型量化相关论文列表，根据模型结构和应用场景对论文进行-
机器学习算法  
细胞基因研究圈
 
重新设计 AAV：通过机器学习改造衣壳
机器学习算法 细胞基因研究圈 昨天
中信证券研究
 
机器学习｜多模态大模型催生产业应用革新，国内迭代追逐势头不减
机器学习算法 中信证券研究 昨天
机器学习算法那些事
 
机器学习博士在获得学位之前需要掌握的几种工具！
机器学习算法 机器学习算法那些事 昨天
Hydro
 
HA. [深度学习] 基于物理机制约束的深度学习：预测非饱和带含水率
机器学习算法 Hydro 昨天
机器学习算法与Python实战
 
入行机器学习非学数学不可？学到什么程度？如何才能提高数学水平？
机器学习算法 机器学习算法与Python实战 昨天
brainnews
 
明晚讲座预告| 对全脑神经环路进行全自动分析的深度学习算法系统
机器学习算法 brainnews 昨天
生态遥感前沿
 
Building and Environment | 利用机器学习方法量化绿地形态空间格局与城市热岛关系
机器学习算法 生态遥感前沿 昨天
 
 
 MediaPipe U：一个帮助你集成人工智能和机器学习技术到-
机器学习算法  天前
计算机视觉研究院
 
传统和深度学习进行结合，较大程度提高人脸检测精度（附论文下载）
机器学习算法 计算机视觉研究院 天前
BioArtMED
 
​NAR｜张世华/陈洛南/合原一幸 合作开发基于深度学习显著图的空间域特异可变基因识别方法-STAMarker
机器学习算法 BioArtMED 天前
知社学术圈
 
Npj Comput. Mater.: 多相态氧化镓—机器学习势函数的试金石
机器学习算法 知社学术圈 天前
亚马逊云科技
 
 年亚马逊云科技全球人工智能和机器学习奖学金计划启动啦
机器学习算法 亚马逊云科技 天前
LAC空间学社
 
当我们和海外院校教授一起探索机器学习、生成算法、游戏引擎与建筑和景观空间结合的可能性！得出的结果是？
机器学习算法 LAC空间学社 天前
专知智能防务
 
《用机器学习模拟激光武器系统的决策支持以打击无人机蜂群》 页论文
机器学习算法 专知智能防务 天前
专知智能防务
 
《基于机器学习的无人机频谱指纹识别：防御性网络战》哈佛 最新 页论文
机器学习算法 专知智能防务 天前
 
 
 机器学习和深度学习应避免的 种错误 - 使用低质量数据——缺失-
机器学习算法  天前
DrugAI
 
使用单一智能手机照片进行分类和监测青少年特发性脊柱侧凸的深度学习模型
机器学习算法 DrugAI 天前
brainnews
 
讲座预告| 对全脑神经环路进行全自动分析的深度学习算法系统
机器学习算法 brainnews 天前
热辐射与微纳光子学
 
纳米光学与机器学习相结合，赋能片上近红外光谱传感
机器学习算法 热辐射与微纳光子学 天前
人工智能学家
 
当机器学习遇见拓扑：拓扑数据分析与拓扑深度学习
机器学习算法 人工智能学家 天前
机器学习初学者
 
 机器学习 动图图解马尔科夫链、PCA、贝叶斯！
机器学习算法 机器学习初学者 天前
ACS美国化学会
 
ACS ES&T Engineering | 集成半监督与自动机器学习预测评估不同预处理方式对污泥厌氧消化产甲烷的影响
机器学习算法 ACS美国化学会 天前
 D视觉工坊
 
项目需求|起步 W！深度学习点云配准方法指导
机器学习算法 D视觉工坊 天前
nanomicroletters
 
机器学习助力柔性力传感技术的发展
机器学习算法 nanomicroletters 天前
DrugAI
 
用于战争后的创伤后应激障碍的机器学习预测模型
机器学习算法 DrugAI 天前
CVer
 
深度学习三巨头论战升级！吴恩达痛批美国AI禁令扼杀开源，马斯克都下场了
机器学习算法 CVer 天前
极市平台
 
传统深度学习在智慧交通中的那些事儿
机器学习算法 极市平台 天前
测序中国
 
Nature | 快速纳米孔测序+机器学习，手术期间实现中枢神经系统肿瘤的准确分类
机器学习算法 测序中国 天前
专知
 
 新书 构建数据和机器学习平台:在云端实现分析和人工智能驱动的创新， 页pdf
机器学习算法 专知 天前
芯思想
 
ICCAD硬件机器学习竞赛落幕，微型机器学习和量子计算两大赛道奖项公榜
机器学习算法 芯思想 天前
机器学习初学者
 
 机器学习 详解XGBoost 重大更新！
机器学习算法 机器学习初学者 天前
机器学习初学者
 
 深度学习 GAN强势归来！ 篇论文总结GAN最新研究
机器学习算法 机器学习初学者 天前
brainnews
 
 讲座预告| 对全脑神经环路进行全自动分析的深度学习算法系统
机器学习算法 brainnews 天前
新机器视觉
 
机器学习最优化算法（全面总结）
机器学习算法 新机器视觉 天前
集智俱乐部
 
当机器学习遇见拓扑：拓扑数据分析与拓扑深度学习
机器学习算法 集智俱乐部 天前
机器学习算法那些事
 
《一书解决几乎所有机器学习问题》.PDF下载
机器学习算法 机器学习算法那些事 天前
nextquestion
 
追问Daily｜SpikingJelly：基于尖峰神经网络的开源机器学习平台；​阿里云发布通义千问 ；​慢波睡眠不足与痴呆症

http://www.python88.com/topic/120218
 Efficient Scaling of Dynamic Graph Neural Networks
 动态图神经网络的有效缩放
 https://arxiv.org/abs/2109.07893
 Venkatesan T. Chakaravarthy,Shivmaran S. Pandian,Saurabh Raje,Yogish Sabharwal,Toyotaro Suzumura,Shashanka Ubaru
 IBM Research, India,  IBM T.J. Watson Research Center
 Conference version to appear in the proceedings of SC'21
 我们提出了在跨多节点、多GPU系统的大规模图上训练动态图神经网络（GNN）的分布式算法。据我们所知，这是第一次对动态GNN进行缩放研究。我们设计了减少GPU内存使用的机制，并确定了两个执行时间瓶颈：CPU-GPU数据传输；和通讯量。利用动态图的特性，我们设计了一种基于图差分的策略来显著减少传输时间。我们开发了一种简单但有效的数据分发技术，在该技术下，对于任意数量的GPU，通信量在输入大小上保持固定和线性。我们在128GPU系统上使用十亿大小的图形进行的实验表明：（i）该分配方案在128GPU上实现了高达30倍的加速比；（ii）图形差分技术将传输时间减少了4.1倍，总执行时间减少了40%
 We present distributed algorithms for training dynamic Graph Neural Networks (GNN) on large scale graphs spanning multi-node, multi-GPU systems. To the best of our knowledge, this is the first scaling study on dynamic GNN. We devise mechanisms for reducing the GPU memory usage and identify two execution time bottlenecks: CPU-GPU data transfer; and communication volume. Exploiting properties of dynamic graphs, we design a graph difference-based strategy to significantly reduce the transfer time. We develop a simple, but effective data distribution technique under which the communication volume remains fixed and linear in the input size, for any number of GPUs. Our experiments using billion-size graphs on a system of 128 GPUs shows that: (i) the distribution scheme achieves up to 30x speedup on 128 GPUs; (ii) the graph-difference technique reduces the transfer time by a factor of up to 4.1x and the overall execution time by up to 40%


 SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and  Interaction Space Graph Reasoning for Autonomous Driving
 Spin Road Mapper：基于空间和交互空间图推理的自动驾驶航拍道路提取
 https://arxiv.org/abs/2109.07701
 Wele Gedara Chaminda Bandara,Jeya Maria Jose Valanarasu,Vishal M. Patel
机构：Authors are with the Department of Electrical and Computer Engi-neering,  The Johns Hopkins University
 None
摘要
：道路提取是构建自主导航系统的关键步骤。检测路段具有挑战性，因为它们具有不同的宽度，在整个图像中分叉，并且经常被地形、云层或其他天气条件遮挡。仅使用卷积神经网络（ConvNets）解决此问题并不有效，因为它在捕获图像中道路段之间的距离依赖关系方面效率低下，这对于提取道路连通性至关重要。为此，我们提出了一个空间和交互空间图形推理（SPIN）模块，当插入ConvNet时，该模块对在从特征地图投影的空间和交互空间上构建的图形执行推理。空间推理提取不同空间区域和其他上下文信息之间的依赖关系。对投影交互空间的推理有助于从图像中显示的其他地形图中恰当地描绘道路。因此，SPIN提取路段之间的长期依赖关系，并从其他语义中有效地描绘道路。我们还介绍了一个自旋金字塔，它在多个尺度上执行自旋图推理，以提取多尺度特征。我们提出了一种基于堆叠沙漏模块和旋转金字塔的道路分割网络，与现有方法相比，该网络具有更好的性能。此外，该方法计算效率高，在训练过程中显著提高了收敛速度，使其适用于大规模高分辨率航空图像。代码可从以下网址获得：https://github.com/wgcban/SPIN_RoadMapper.git.
 Road extraction is an essential step in building autonomous navigation systems. Detecting road segments is challenging as they are of varying widths, bifurcated throughout the image, and are often occluded by terrain, cloud, or other weather conditions. Using just convolution neural networks (ConvNets) for this problem is not effective as it is inefficient at capturing distant dependencies between road segments in the image which is essential to extract road connectivity. To this end, we propose a Spatial and Interaction Space Graph Reasoning (SPIN) module which when plugged into a ConvNet performs reasoning over graphs constructed on spatial and interaction spaces projected from the feature maps. Reasoning over spatial space extracts dependencies between different spatial regions and other contextual information. Reasoning over a projected interaction space helps in appropriate delineation of roads from other topographies present in the image. Thus, SPIN extracts long-range dependencies between road segments and effectively delineates roads from other semantics. We also introduce a SPIN pyramid which performs SPIN graph reasoning across multiple scales to extract multi-scale features. We propose a network based on stacked hourglass modules and SPIN pyramid for road segmentation which achieves better performance compared to existing methods. Moreover, our method is computationally efficient and significantly boosts the convergence speed during training, making it feasible for applying on large-scale high-resolution aerial images. Code available at: https://github.com/wgcban/SPIN_RoadMapper.git.


 Comparing Euclidean and Hyperbolic Embeddings on the WordNet Nouns  Hypernymy Graph
 WordNet名词Hypernymy图上欧几里得和双曲嵌入的比较
 https://arxiv.org/abs/2109.07488
 Sameer Bansal,Adrian Benton
机构：Bloomberg,  Lexington Ave, New York, NY , USA
 Nickel和Kiela（2017）提出了一种在庞加莱球中嵌入树节点的新方法，并指出这些双曲型嵌入在嵌入大型层次结构图（如WordNet名词超名树）节点时远比欧几里德嵌入有效。在低维情况下尤其如此（Nickel和Kiela，2017年，表1）。在这项工作中，我们试图重现他们嵌入和重建WordNet名词超义图的实验。与他们的报告相反，我们发现欧几里德嵌入能够表示这棵树，当至少允许50维时，欧几里德嵌入至少能够表示庞加莱嵌入。我们注意到，鉴于双曲嵌入在极低维环境中令人印象深刻的性能，这并没有削弱他们工作的重要性。然而，考虑到他们工作的广泛影响，我们的目标是在欧几里德嵌入和双曲嵌入之间进行更新和更精确的比较。
 Nickel and Kiela (2017) present a new method for embedding tree nodes in the Poincare ball, and suggest that these hyperbolic embeddings are far more effective than Euclidean embeddings at embedding nodes in large, hierarchically structured graphs like the WordNet nouns hypernymy tree. This is especially true in low dimensions (Nickel and Kiela, 2017, Table 1). In this work, we seek to reproduce their experiments on embedding and reconstructing the WordNet nouns hypernymy graph. Counter to what they report, we find that Euclidean embeddings are able to represent this tree at least as well as Poincare embeddings, when allowed at least 50 dimensions. We note that this does not diminish the significance of their work given the impressive performance of hyperbolic embeddings in very low-dimensional settings. However, given the wide influence of their work, our aim here is to present an updated and more accurate comparison between the Euclidean and hyperbolic embeddings.


 RaWaNet: Enriching Graph Neural Network Input via Random Walks on Graphs
 RaWaNet：利用图上随机游走丰富图神经网络输入
 https://arxiv.org/abs/2109.07555
 Anahita Iravanizad,Edgar Ivan Sanchez Medina,Martin Stoll
 近年来，图形神经网络（GNN）越来越受欢迎，对于以图形表示的数据显示了非常有希望的结果。大多数GNN架构都是基于开发新的卷积和/或池层而设计的，这些层可以更好地提取用于不同预测任务的图的隐藏和深层表示。这些层的输入主要是图形的三个默认描述符：节点特征$（X）$、邻接矩阵$（a）$和边特征$（W）$（如果可用）。为了给网络提供更丰富的输入，我们提出了一种基于三个选定长度的图的随机游走数据处理方法。即，长度为1和2的（规则）行走，以及长度为$\gamma\in（0,1）$的分数行走，以捕捉图上不同的局部和全局动态。我们还计算每个随机游动的平稳分布，然后将其用作初始节点特征的比例因子（$X$）。这样，对于每个图，网络接收多个邻接矩阵及其对节点特征的单独权重。我们通过将处理后的节点特征传递给网络，在各种分子数据集上测试我们的方法，以便执行一些分类和回归任务。有趣的是，我们的方法没有使用在分子图学习中被大量利用的边缘特征，使浅层网络优于众所周知的深层GNN。
 In recent years, graph neural networks (GNNs) have gained increasing popularity and have shown very promising results for data that are represented by graphs. The majority of GNN architectures are designed based on developing new convolutional and/or pooling layers that better extract the hidden and deeper representations of the graphs to be used for different prediction tasks. The inputs to these layers are mainly the three default descriptors of a graph, node features $(X)$, adjacency matrix $(A)$, and edge features $(W)$ (if available). To provide a more enriched input to the network, we propose a random walk data processing of the graphs based on three selected lengths. Namely, (regular) walks of length 1 and 2, and a fractional walk of length $\gamma \in (0,1)$, in order to capture the different local and global dynamics on the graphs. We also calculate the stationary distribution of each random walk, which is then used as a scaling factor for the initial node features ($X$). This way, for each graph, the network receives multiple adjacency matrices along with their individual weighting for the node features. We test our method on various molecular datasets by passing the processed node features to the network in order to perform several classification and regression tasks. Interestingly, our method, not using edge features which are heavily exploited in molecular graph learning, let a shallow network outperform well known deep GNNs.


Transformer(1篇)

  An End-to-End Transformer Model for 3D Object Detection
 一种用于三维目标检测的端到端Transformer模型
 https://arxiv.org/abs/2109.08141
 Ishan Misra,Rohit Girdhar,Armand Joulin
机构：Facebook AI Research
 Accepted at ICCV 2021
 我们提出了3DETR，一种基于端到端转换器的三维点云目标检测模型。与使用大量3D特定感应偏压的现有检测方法相比，3DETR只需对普通Transformer块进行最小修改。具体而言，我们发现，具有非参数查询和傅里叶位置嵌入的标准转换器与使用具有手动调整超参数的三维特定运算符库的专用体系结构具有竞争力。尽管如此，3DETR在概念上简单且易于实现，通过结合3D领域知识实现了进一步的改进。通过大量的实验，我们发现3DETR在具有挑战性的ScanNetV2数据集上的性能比完善且高度优化的VoteNet基线高9.5%。此外，我们还表明3DETR适用于检测不到的3D任务，可以作为未来研究的基础。
 We propose 3DETR, an end-to-end Transformer based object detection model for 3D point clouds. Compared to existing detection methods that employ a number of 3D-specific inductive biases, 3DETR requires minimal modifications to the vanilla Transformer block. Specifically, we find that a standard Transformer with non-parametric queries and Fourier positional embeddings is competitive with specialized architectures that employ libraries of 3D-specific operators with hand-tuned hyperparameters. Nevertheless, 3DETR is conceptually simple and easy to implement, enabling further improvements by incorporating 3D domain knowledge. Through extensive experiments, we show 3DETR outperforms the well-established and highly optimized VoteNet baselines on the challenging ScanNetV2 dataset by 9.5%. Furthermore, we show 3DETR is applicable to 3D tasks beyond detection, and can serve as a building block for future research.


GAN|对抗|攻击|生成相关(5篇)

【1】 Zero-Shot Open Information Extraction using Question Generation and  Reading Comprehension
 基于问题生成和阅读理解的零命中率开放信息抽取
 https://arxiv.org/abs/2109.08079
 Himanshu Gupta,Amogh Badugu,Tamanna Agrawal,Himanshu Sharad Bhatt
机构：American Express, AI Labs, Bangalore, India, Himanshu S. Bhatt
 8 pages, 2 Figures, 1 Algorithm, 7 Tables. Accepted in KDD Workshop on Machine Learning in Finance 2021
摘要
：通常，开放信息提取（OpenIE）侧重于提取表示主题、关系和关系对象的三元组。然而，大多数现有技术都是基于每个域中预定义的一组关系，这将它们的适用性限制在新的域中，这些域中的关系可能是未知的，例如金融文档。本文提出了一种Zero-Shot开放信息提取技术，该技术利用现成的机器阅读理解（MRC）模型从句子中提取实体（值）及其描述（键）。该模型的输入问题是使用一种新的名词短语生成方法生成的。这种方法考虑了句子的上下文，可以产生各种各样的问题，使我们的技术领域独立。给定问题和句子，我们的技术使用MRC模型来提取实体（值）。与问题相对应的具有最高置信度的名词短语作为描述（键）。本文还介绍了EDGAR10-Q数据集，该数据集基于美国证券交易委员会（SEC）上市公司的公开财务文件。该数据集由段落、标记值（实体）及其键（描述）组成，是实体提取数据集中最大的数据集之一。该数据集将成为研究界的宝贵补充，尤其是在金融领域。最后，本文在EDGAR10-Q和Ade语料库药物剂量数据集上证明了该技术的有效性，其准确率分别为86.84%和97%。
 Typically, Open Information Extraction (OpenIE) focuses on extracting triples, representing a subject, a relation, and the object of the relation. However, most of the existing techniques are based on a predefined set of relations in each domain which limits their applicability to newer domains where these relations may be unknown such as financial documents. This paper presents a zero-shot open information extraction technique that extracts the entities (value) and their descriptions (key) from a sentence, using off the shelf machine reading comprehension (MRC) Model. The input questions to this model are created using a novel noun phrase generation method. This method takes the context of the sentence into account and can create a wide variety of questions making our technique domain independent. Given the questions and the sentence, our technique uses the MRC model to extract entities (value). The noun phrase corresponding to the question, with the highest confidence, is taken as the description (key).  This paper also introduces the EDGAR10-Q dataset which is based on publicly available financial documents from corporations listed in US securities and exchange commission (SEC). The dataset consists of paragraphs, tagged values (entities), and their keys (descriptions) and is one of the largest among entity extraction datasets. This dataset will be a valuable addition to the research community, especially in the financial domain. Finally, the paper demonstrates the efficacy of the proposed technique on the EDGAR10-Q and Ade corpus drug dosage datasets, where it obtained 86.84 % and 97% accuracy, respectively.


 Membership Inference Attacks Against Recommender Systems
 针对推荐系统的成员推理攻击
 https://arxiv.org/abs/2109.08045
 Minxing Zhang,Zhaochun Ren,Zihan Wang,Pengjie Ren,Zhumin Chen,Pengfei Hu,Yang Zhang
机构：Shandong University, CISPA Helmholtz Center for Information Security
 近年来，推荐系统取得了良好的性能，成为应用最广泛的web应用之一。然而，推荐系统通常针对高度敏感的用户数据进行训练，因此，推荐系统中潜在的数据泄漏可能会导致严重的隐私问题。在本文中，我们首次尝试通过成员推理的角度来量化推荐系统的隐私泄漏。与针对机器学习分类器的传统隶属度推理相比，我们的攻击面临两个主要区别。首先，我们的攻击是在用户级别，而不是在数据样本级别。其次，对手只能从推荐系统中观察到有序的推荐项目，而不能以后验概率的形式观察预测结果。为了解决上述挑战，我们提出了一种新的方法，从相关项目中表示用户。此外，还建立了一个阴影推荐器，用于导出用于训练攻击模型的标记训练数据。大量的实验结果表明，我们的攻击框架具有很强的性能。此外，我们还设计了一种防御机制来有效地缓解推荐系统的成员推理威胁。
 Recently, recommender systems have achieved promising performances and become one of the most widely used web applications. However, recommender systems are often trained on highly sensitive user data, thus potential data leakage from recommender systems may lead to severe privacy problems.  In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference. In contrast with traditional membership inference against machine learning classifiers, our attack faces two main differences. First, our attack is on the user-level but not on the data sample-level. Second, the adversary can only observe the ordered recommended items from a recommender system instead of prediction results in the form of posterior probabilities. To address the above challenges, we propose a novel method by representing users from relevant items. Moreover, a shadow recommender is established to derive the labeled training data for training the attack model. Extensive experimental results show that our attack framework achieves a strong performance. In addition, we design a defense mechanism to effectively mitigate the membership inference threat of recommender systems.


 KnowMAN: Weakly Supervised Multinomial Adversarial Networks
 KnowMAN：弱监督多项式对抗网络
 https://arxiv.org/abs/2109.07994
 Luisa März,Ehsaneddin Asgari,Fabienne Braune,Franziska Zimmermann,Benjamin Roth
机构：⋄ Digital Philology, Research Group Data Mining and Machine Learning, University of Vienna, Austria, † NLP Expert Center, Data:Lab, Volkswagen AG, Munich, Germany
 9 pages, 3 figures, 2 tables, accepted to EMNLP 2021
 训练神经模型时缺少标记数据的问题通常通过利用有关特定任务的知识来解决，从而产生启发式但有噪声的标记。知识被捕获到标签函数中，标签函数检测训练样本中的某些规则或模式，并注释相应的标签进行训练。这种弱监督训练过程可能会导致过度依赖由标记函数捕获的信号，并阻碍模型利用其他信号或很好地推广。我们提出KnowMAN，这是一种对抗性方案，能够控制与特定标记功能相关的信号的影响。KnowMAN强制网络学习对这些信号不变的表示，并拾取与输出标签更普遍相关的其他信号。与使用预先训练的transformer语言模型和基于特征的基线的直接弱监督学习相比，KnowMAN极大地改善了结果。
 The absence of labeled data for training neural models is often addressed by leveraging knowledge about the specific task, resulting in heuristic but noisy labels. The knowledge is captured in labeling functions, which detect certain regularities or patterns in the training samples and annotate corresponding labels for training. This process of weakly supervised training may result in an over-reliance on the signals captured by the labeling functions and hinder models to exploit other signals or to generalize well. We propose KnowMAN, an adversarial scheme that enables to control influence of signals associated with specific labeling functions. KnowMAN forces the network to learn representations that are invariant to those signals and to pick up other signals that are more generally associated with an output label. KnowMAN strongly improves results compared to direct weakly supervised learning with a pre-trained transformer language model and a feature-based baseline.