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

Effective and Efficient Representati...

Chen, Ting.

Linked to FindBook

Google Book

Amazon

博客來

Effective and Efficient Representation Learning for Graph Structures.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Effective and Efficient Representation Learning for Graph Structures./
Author:	Chen, Ting.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2019,
Description:	149 p.
Notes:	Source: Dissertations Abstracts International, Volume: 80-10, Section: B.
Contained By:	Dissertations Abstracts International80-10B.
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13810372
ISBN:	9781392010143

Effective and Efficient Representation Learning for Graph Structures.
Chen, Ting.

Effective and Efficient Representation Learning for Graph Structures. - Ann Arbor : ProQuest Dissertations & Theses, 2019 - 149 p.

Source: Dissertations Abstracts International, Volume: 80-10, Section: B.

Thesis (Ph.D.)--University of California, Los Angeles, 2019.

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

Graph structures are a powerful abstraction of many real-world data, such as human interactions and information networks. Despite the powerful abstraction, graphs are challenging to model due to the high-dimensional, irregular and heterogeneous characteristics of many real-world graph data. An essential problem arose is how to effectively and efficiently learn the representation for objects in graphs. In this thesis, both the effectiveness as well as efficiency aspects of the graph representation learning problem are addressed. Specifically, we start by proposing an effective approach for learning heterogeneous graph embedding in an unsupervised setting. Then this is generalized to semi-supervised scenario where label guidance is leveraged. The effective graph representation learning models are followed by efficient techniques, where we propose efficient sampling strategies to improve the training efficiency for content-rich graph embedding models. Finally, to reduce storage and memory cost of the embedding table used in various models, we introduce a framework based on KD code, which can compress the embedding table in an end-to-end fashion. We conduct extensive experiments on various real-world tasks on graph data (e.g. anomaly detection, recommendation and text classifications), and the empirical results validate both effectiveness as well as efficiency of our proposed algorithms.

ISBN: 9781392010143Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Content-rich graph embedding

Effective and Efficient Representation Learning for Graph Structures.
LDR:02587nmm a2200349 4500 001 2268631
005 20200824072416.5
008 220629s2019 ||||||||||||||||| ||eng d
020 $a 9781392010143
035 $a (MiAaPQ)AAI13810372
035 $a (MiAaPQ)ucla:17585
035 $a AAI13810372
040 $a MiAaPQ $c MiAaPQ
100 1 $a Chen, Ting. $3 1287144
245 1 0 $a Effective and Efficient Representation Learning for Graph Structures.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2019
300 $a 149 p.
500 $a Source: Dissertations Abstracts International, Volume: 80-10, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Sun, Yizhou.
502 $a Thesis (Ph.D.)--University of California, Los Angeles, 2019.
506 $a This item must not be sold to any third party vendors.
520 $a Graph structures are a powerful abstraction of many real-world data, such as human interactions and information networks. Despite the powerful abstraction, graphs are challenging to model due to the high-dimensional, irregular and heterogeneous characteristics of many real-world graph data. An essential problem arose is how to effectively and efficiently learn the representation for objects in graphs. In this thesis, both the effectiveness as well as efficiency aspects of the graph representation learning problem are addressed. Specifically, we start by proposing an effective approach for learning heterogeneous graph embedding in an unsupervised setting. Then this is generalized to semi-supervised scenario where label guidance is leveraged. The effective graph representation learning models are followed by efficient techniques, where we propose efficient sampling strategies to improve the training efficiency for content-rich graph embedding models. Finally, to reduce storage and memory cost of the embedding table used in various models, we introduce a framework based on KD code, which can compress the embedding table in an end-to-end fashion. We conduct extensive experiments on various real-world tasks on graph data (e.g. anomaly detection, recommendation and text classifications), and the empirical results validate both effectiveness as well as efficiency of our proposed algorithms.
590 $a School code: 0031.
650 4 $a Computer science. $3 523869
653 $a Content-rich graph embedding
653 $a Heterogeneous graph embedding
653 $a Real-world graph data
690 $a 0984
710 2 $a University of California, Los Angeles. $b Computer Science. $3 2104007
773 0 $t Dissertations Abstracts International $g 80-10B.
790 $a 0031
791 $a Ph.D.
792 $a 2019
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=13810372