没有合适的资源？快使用搜索试试~ 我知道了~

首页Deeplearning with graph structured representations.pdf

Deeplearning with graph structured representations.pdf

DeepLearning

需积分: 0 9 下载量 95 浏览量更新于2023-05-13 评论收藏 8.7MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

试读

178页

图卷积神经网络--Thomas Kipf 的PHD论文，涵盖GCN的基本理论以及在无监督学习的应用。

资源详情

资源评论

资源推荐

UvA-DARE is a service provided by the library of the University of Amsterdam (http://dare.uva.nl)

UvA-DARE (Digital Academic Repository)

Deep learning with graph-structured representations

Kipf, T.N.

Link to publication

Creative Commons License (see https://creativecommons.org/use-remix/cc-licenses):

Other

Citation for published version (APA):

Kipf, T. N. (2020). Deep learning with graph-structured representations.

General rights

It is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s),

other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons).

Disclaimer/Complaints regulations

If you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating

your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask

the Library: https://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam,

The Netherlands. You will be contacted as soon as possible.

Download date: 13 May 2020

Deep Learning with

Graph-Structured

Representations

Deep Learning with Graph-Structured Representations Thomas Kipf

Thomas Kipf

Deep Learning with

Graph-Structured Representations

ACADEMISCH PROEFSCHRIFT

ter verkrijging van de graad van doctor

aan de Universiteit van Amsterdam

op gezag van de Rector Magniﬁcus

prof. dr. ir. K.I.J. Maex

ten overstaan van een door het College voor Promoties

ingestelde commissie,

in het openbaar te verdedigen

op donderdag 23 april 2020, te 14.00 uur

door

Thomas Norbert Kipf

geboren te Roth

P R O M O T I E C O M M I S S I E

Promotor:

prof. dr. M. Welling Universiteit van Amsterdam

Copromotor:

dr. I.A. Titov University of Edinburgh

Overige leden:

prof. dr. M.M. Bronstein Imperial College London

prof. dr. F.A.H. van Harmelen Vrije Universiteit Amsterdam

prof. dr. M. de Rijke Universiteit van Amsterdam

dr. P.W. Battaglia DeepMind Technologies Ltd

dr. H.C. van Hoof Universiteit van Amsterdam

Faculteit der Natuurwetenschappen, Wiskunde en Informatica

The work described in this thesis has been primarily carried out at the Ams-

terdam Machine Learning Lab (AMLab) of the University of Amsterdam and

in part during an internship at DeepMind Technologies Ltd, London, UK. The

research carried out at the University of Amsterdam was funded by SAP SE.

Printed by Ridderprint, The Netherlands.

ISBN: 978-94-6375-851-2

 2020 by T. N. Kipf, Amsterdam, The Netherlands.

S U M M A R Y

In this thesis, Deep Learning with Graph-Structured Representations, we propose

novel approaches to machine learning with structured data. Our proposed

methods are largely based on the theme of structuring the representations and

computations of neural network-based models in the form of a graph, which

allows for improved generalization when learning from data with both explicit

and implicit modular structure.

Our contributions are as follows:

• We propose graph convolutional networks (GCNs) (Kipf and Welling,

2017; Chapter 3) for semi-supervised classiﬁcation of nodes in graph-

structured data. GCNs are a form of graph neural network that per-

form parameterized message-passing operations in a graph, modeled as a

ﬁrst-order approximation to spectral graph convolutions. GCNs achieved

state-of-the-art performance in node-level classiﬁcation tasks in a number

of undirected graph datasets at the time of publication.

• We propose graph auto-encoders (GAEs) (Kipf and Welling, 2016; Chap-

ter 4) for unsupervised learning and link prediction in graph-structured

data. GAEs utilize an encoder based on graph neural networks and a

decoder that reconstructs links in a graph based on a pairwise scoring

function. We further propose a model variant framed as a probabilistic

generative model that is trained using variational inference, which we

name variational GAE. GAEs and variational GAEs are particularly suited

for representation learning on graphs in the absence of node labels.

• We propose relational GCNs (Schlichtkrull and Kipf et al., 2018; Chapter

5) that extend the GCN model to directed, relational graphs with multi-

ple edge types. Relational GCNs are well-suited for modeling relational

data and we demonstrate an application to semi-supervised entity classi-

ﬁcation in knowledge bases.

iii

剩余177页未读，继续阅读

项目结构 ├── CMakeLists.txt ├── README.md └── compiler ── CMakeLists.txt ──ast.h/ast.cpp ── IR.cpp/IR.txt ── parser.y ── scanner.l ── table.cpp/table.h ── main.cpp ── graph_ast.cpp ── graph_flow.cpp ── graph_table.cpp，应该先从哪一个代码开始读？

其中包含了词法分析器（scanner.l）、语法分析器（parser.y）、抽象语法树（ast.h/ast.cpp）、符号表（table.cpp/table.h）、中间代码生成（IR.cpp/IR.txt）以及一些可视化的部分（graph_ast.cpp、graph_flow.cpp、...

我有多组包含空间坐标的路径信息, 现在要用DeepLearning4j训练模型, 从而实现给定起止点坐标, 自动计算运动路径, 应该怎么做, 请给出具体代码

import org.deeplearning4j.nn.graph.ComputationGraph; import org.deeplearning4j.nn.multilayer.MultiLayerNetwork; import org.deeplearning4j.nn.weights.WeightInit; import org.deeplearning4j.optimize....

graph.cypher.execute

除了graph.cypher.execute方法之外，Neo4j还提供了其他一些方法来执行Cypher查询，如graph.run、graph.evaluate等，它们的用法和功能略有不同，但都可以实现对图数据库的查询和操作。总之，graph.cypher.execute...

代码报错--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) <ipython-input-35-480e4084491e> in <cell line: 13>() 12 graph = tf.Graph() 13 with graph.as_default(): ---> 14 od_graph_def = tf.GraphDef() 15 with tf.io.gfile.GFile(model_filename, 'rb') as fid: 16 serialized_graph = fid.read() AttributeError: module 'tensorflow' has no attribute 'GraphDef'

with graph.as_default(): od_graph_def = tf.compat.v1.GraphDef() with tf.io.gfile.GFile(model_filename, 'rb') as fid: serialized_graph = fid.read() od_graph_def.ParseFromString(serialized_graph) ...

graph.db.dump

graph.db.dump是一个与图数据库相关的术语，指的是将图数据库中的数据导出为一个文件（通常是二进制文件或文本文件）。通过使用graph.db.dump命令，我们可以将整个图数据库的内容保存到一个文件中，以便备份、迁移或...

如果你是一个安卓开发程序员你在访问https://graph.microsoft.com/v1.0/me成功返回token但是访问https://graph.microsoft.com/v1.0/me/drive/报错token为空之后你要怎么判断是哪里出了问题如何解决这个问题

如果在访问https://graph.microsoft.com/v1.0/me/drive/时报错token为空，可能是由于以下原因： 1. 网络连接问题：在访问https://graph.microsoft.com/v1.0/me/drive/时，你需要确保设备已连接到互联网。请检查你的...

将这两个代码结合import cv2 import numpy as np import urllib.request import tensorflow as tf # 下载DeepLabv3+模型权重文件 model_url = "http://download.tensorflow.org/models/deeplabv3_mnv2_pascal_train_aug_2018_01_29.tar.gz" tar_filename = "deeplabv3_mnv2_pascal_train_aug.tar.gz" urllib.request.urlretrieve(model_url, tar_filename) # 解压缩 with tarfile.open(tar_filename, "r:gz") as tar: tar.extractall() model_filename = "deeplabv3_mnv2_pascal_train_aug/frozen_inference_graph.pb" # 加载模型 graph = tf.Graph() with graph.as_default(): od_graph_def = tf.GraphDef() with tf.io.gfile.GFile(model_filename, 'rb') as fid: serialized_graph = fid.read() od_graph_def.ParseFromString(serialized_graph) tf.import_graph_def(od_graph_def, name='') # 读取图像 image_path = "your_image.jpg" image = cv2.imread(image_path) # 进行图像分割 with tf.compat.v1.Session(graph=graph) as sess: input_tensor = graph.get_tensor_by_name('ImageTensor:0') output_tensor = graph.get_tensor_by_name('SemanticPredictions:0') output = sess.run(output_tensor, feed_dict={input_tensor: image}) # 解码并可视化分割结果 segmentation_mask = np.squeeze(output) segmentation_mask = np.uint8(segmentation_mask) segmentation_mask = cv2.resize(segmentation_mask, (image.shape[1], image.shape[0]), interpolation=cv2.INTER_NEAREST) # 显示原始图像和分割结果 cv2.imshow("Image", image) cv2.imshow("Segmentation Mask", segmentation_mask) cv2.waitKey(0) cv2.destroyAllWindows() model1 = models.CellposeModel(gpu=True, model_type='livecell') model2 = models.Cellpose(gpu=True,model_type='nuclei') model3= models.Cellpose(gpu=True,model_type='cyto2') 集成DeepLabv3+模型和cellpose模型

with graph.as_default(): od_graph_def = tf.GraphDef() with tf.io.gfile.GFile(model_filename, 'rb') as fid: serialized_graph = fid.read() od_graph_def.ParseFromString(serialized_graph) tf.import_...

严重性代码说明项目文件行禁止显示状态错误 Expected an include at the top of the header: '#include "Ed_Graph.generated.h"' GraphPlugin C:\Users\ADMIN\Documents\Unreal Projects\GraphPlugin\Source\GraphPlugin\Public\Ed_Graph.h 18

这个错误提示是由 Unreal Engine 编译器生成的，意味着在头文件 "Ed_Graph.h" 中缺少了一个预期的 include。根据错误提示信息，你需要在头文件 "Ed_Graph.h" 的顶部添加一个预编译指令 "#include "Ed_Graph....

graph = image.img_to_graph(img, mask=mask) graph.data = np.exp(-graph.data / graph.data.std()) labels = spectral_clustering(graph, n_clusters=2, eigen_solver="arpack") label_im = np.full(mask.shape, -1.0) label_im[mask] = labels这段的代码是什么意思

2. `graph.data = np.exp(-graph.data / graph.data.std())` 对图形中的每个像素之间的边进行加权，即计算欧几里得距离并进行指数变换，这可以增强相邻像素之间的关联性，使得它们更可能被分配到同一类别。...

Neo4j版本升高不能使用graph.cypher.execute

zybjtu

粉丝: 72
资源: 22

上传资源快速赚钱

我的内容管理收起

我的资源快来上传第一个资源

我的收益

登录查看自己的收益

我的积分登录查看自己的积分

我的C币登录后查看C币余额

我的收藏

我的下载

下载帮助

会员权益专享

Deeplearning with graph structured representations.pdf

评论0

会员权益专享

最新资源

Deeplearning with graph structured representations.pdf

评论0

图表示深度学习综述（Deep Learning for Learning Graph Representations）【清华大学朱文武老师】.zip

通过SR-GNN算法进行挖掘商品图的时序商品推荐-数据集

基于深度学习的图表示学习方法综述（Deep Learning for Learning Graph Representations）.pdf

我有多组包含空间坐标的路径信息, 现在要用DeepLearning4j训练模型, 从而实现给定起止点坐标, 自动计算运动路径, 应该怎么做, 请给出具体代码

graph.cypher.execute

graph.db.dump

如果你是一个安卓开发程序员你在访问https://graph.microsoft.com/v1.0/me成功返回token但是访问https://graph.microsoft.com/v1.0/me/drive/报错token为空之后你要怎么判断是哪里出了问题如何解决这个问题

安卓开发访问https://graph.microsoft.com/v1.0/me成功返回token但是访问https://graph.microsoft.com/v1.0/me/drive/报错token为空

graph_opt.pb

请以期刊引用的格式，生成GNN（图神经网络）的三篇英文参考文献，注意真实性与权威性

严重性 代码 说明 项目 文件 行 禁止显示状态 错误 Expected an include at the top of the header: '#include "Ed_Graph.generated.h"' GraphPlugin C:\Users\ADMIN\Documents\Unreal Projects\GraphPlugin\Source\GraphPlugin\Public\Ed_Graph.h 18

tf.Graph().as_default():

2020年到2023年深度学习掌纹分类方法有什么，至少10个

tf.graph().as_default()

The Session graph is empty. Add operations to the graph before calling run().

graph = image.img_to_graph(img, mask=mask) graph.data = np.exp(-graph.data / graph.data.std()) labels = spectral_clustering(graph, n_clusters=2, eigen_solver="arpack") label_im = np.full(mask.shape, -1.0) label_im[mask] = labels这段的代码是什么意思

Neo4j版本升高不能使用graph.cypher.execute

会员权益专享

最新资源

严重性代码说明项目文件行禁止显示状态错误 Expected an include at the top of the header: '#include "Ed_Graph.generated.h"' GraphPlugin C:\Users\ADMIN\Documents\Unreal Projects\GraphPlugin\Source\GraphPlugin\Public\Ed_Graph.h 18