東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Deep Generative Models for Images, T...

Cai, Lei.

Linked to FindBook

Google Book

Amazon

博客來

Deep Generative Models for Images, Texts, and Graphs.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep Generative Models for Images, Texts, and Graphs./
Author:	Cai, Lei.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	170 p.
Notes:	Source: Dissertations Abstracts International, Volume: 82-04, Section: B.
Contained By:	Dissertations Abstracts International82-04B.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27743239
ISBN:	9798678105202

Deep Generative Models for Images, Texts, and Graphs.
Cai, Lei.

Deep Generative Models for Images, Texts, and Graphs. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 170 p.

Source: Dissertations Abstracts International, Volume: 82-04, Section: B.

Thesis (Ph.D.)--Washington State University, 2020.

This item must not be sold to any third party vendors.

Generative models have become a powerful unsupervised learning method that can learn the distribution from existing data and generate new samples following the same distribution. With the advances of deep learning, deep generative models have shown promising performance in learning the distribution of complex data. Deep generative models have been applied to a wide range of applications, including image, text, and graph generation tasks. In most real-world applications, data are represented as images, texts, and graphs. This dissertation develops novel, deep generative models toward solving efficiency and accuracy problems in image, text, and graph analysis tasks. More specifically, these deep generative models are designed for improving three tasks; those are multi-modality missing data completion for Alzheimer's disease diagnosis, dialogue generation, and graph link prediction. I mainly focus on generating high-quality samples to facilitate the data analyses in these tasks. The meaning of high quality samples is specific to each different task. In missing data completion tasks, clear and informative images are required for disease diagnosis. In dialogue generation, diverse and reasonable responses for the given dialogue context are critical for improved communication. In graph link prediction, generating potential or missing links in the network with high confidence leads to greater prediction accuracy.In this dissertation, I analyze the limitations and drawbacks of existing models and methods for solving the three tasks. To overcome these limitations, the following four deep generative models are proposed for the tasks. An encoder-decoder network optimized by a combination of three loss functions is developed to generative clear and informative images. A conditional dialogue generation model associated with novel discriminator networks is proposed to generate diverse and reasonable responses. A multi-scale link prediction framework that employs a new node aggregation method to transform the graph into different scales is designed to perform link prediction. A line graph neural networks model, where the original graph is transformed into a corresponding line graph to enable efficient feature learning for the target link, is developed for link prediction tasks. Experimental results demonstrate that the proposed models are able to achieve promising, improved performance on image, text, and graph tasks.

ISBN: 9798678105202Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Deep generative model

Deep Generative Models for Images, Texts, and Graphs.
LDR:03760nmm a2200433 4500 001 2283366
005 20211029101429.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798678105202
035 $a (MiAaPQ)AAI27743239
035 $a AAI27743239
040 $a MiAaPQ $c MiAaPQ
100 1 $a Cai, Lei. $3 3562324
245 1 0 $a Deep Generative Models for Images, Texts, and Graphs.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 170 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-04, Section: B.
500 $a Advisor: Ji, Shuiwang.
502 $a Thesis (Ph.D.)--Washington State University, 2020.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a Generative models have become a powerful unsupervised learning method that can learn the distribution from existing data and generate new samples following the same distribution. With the advances of deep learning, deep generative models have shown promising performance in learning the distribution of complex data. Deep generative models have been applied to a wide range of applications, including image, text, and graph generation tasks. In most real-world applications, data are represented as images, texts, and graphs. This dissertation develops novel, deep generative models toward solving efficiency and accuracy problems in image, text, and graph analysis tasks. More specifically, these deep generative models are designed for improving three tasks; those are multi-modality missing data completion for Alzheimer's disease diagnosis, dialogue generation, and graph link prediction. I mainly focus on generating high-quality samples to facilitate the data analyses in these tasks. The meaning of high quality samples is specific to each different task. In missing data completion tasks, clear and informative images are required for disease diagnosis. In dialogue generation, diverse and reasonable responses for the given dialogue context are critical for improved communication. In graph link prediction, generating potential or missing links in the network with high confidence leads to greater prediction accuracy.In this dissertation, I analyze the limitations and drawbacks of existing models and methods for solving the three tasks. To overcome these limitations, the following four deep generative models are proposed for the tasks. An encoder-decoder network optimized by a combination of three loss functions is developed to generative clear and informative images. A conditional dialogue generation model associated with novel discriminator networks is proposed to generate diverse and reasonable responses. A multi-scale link prediction framework that employs a new node aggregation method to transform the graph into different scales is designed to perform link prediction. A line graph neural networks model, where the original graph is transformed into a corresponding line graph to enable efficient feature learning for the target link, is developed for link prediction tasks. Experimental results demonstrate that the proposed models are able to achieve promising, improved performance on image, text, and graph tasks.
590 $a School code: 0251.
650 4 $a Computer science. $3 523869
650 4 $a Health education. $3 559086
650 4 $a Epidemiology. $3 568544
650 4 $a Neurosciences. $3 588700
650 4 $a Educational technology. $3 517670
650 4 $a Pathology. $3 643180
650 4 $a Multimedia communications. $3 590562
653 $a Deep generative model
653 $a Learning methods
653 $a Complex data
653 $a Alzheimer's disease
653 $a Graph link prediction
690 $a 0984
690 $a 0680
690 $a 0571
690 $a 0558
690 $a 0317
690 $a 0710
690 $a 0766
710 2 $a Washington State University. $b Computer Science. $3 3174108
773 0 $t Dissertations Abstracts International $g 82-04B.
790 $a 0251
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27743239