東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Representation Learning and Algorithms in Hyperbolic Spaces.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Representation Learning and Algorithms in Hyperbolic Spaces./
作者:	Chami, Ines.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	193 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
標題:	Taxonomy. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28688401
ISBN:	9798544204398

Representation Learning and Algorithms in Hyperbolic Spaces.
Chami, Ines.

Representation Learning and Algorithms in Hyperbolic Spaces. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 193 p.

Source: Dissertations Abstracts International, Volume: 83-05, Section: B.

Thesis (Ph.D.)--Stanford University, 2021.

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

Graph embedding methods aim at learning representations of nodes that preserve graph properties (e.g., graph distances). These embeddings can then be used in downstream applications such as clustering, visualization, nearest neighbor search and classification tasks. Most machine learning algorithms learn embeddings in standard Euclidean spaces. Recent research shows promise for more faithful embeddings by leveraging non-Euclidean geometries, such as hyperbolic or spherical geometries. In particular, trees can be embedded almost perfectly into two-dimensional hyperbolic spaces, while this is not possible in Euclidean spaces of any dimension. In this thesis, we develop machine learning models that operate in hyperbolic spaces. We start by introducing hyperbolic representation learning methods for hierarchical graphs, including methods for multi relational graphs or graphs with node features. We demonstrate the benefits of these hyperbolic representations compared to their Euclidean counterparts on a variety of link prediction benchmark datasets. We then design algorithms that operate on these hyperbolic representations. We first propose a method for hierarchical clustering in hyperbolic space, which can be used to solve any similarity-based hierarchical clustering problem with gradient-descent. We then propose a generalization of Principal Component Analysis for hyperbolic inputs, and show that it yields improved low-dimensional representations and data visualizations compared to previous manifold dimensionality reduction methods.

ISBN: 9798544204398Subjects--Topical Terms:

3556303
Taxonomy.

Representation Learning and Algorithms in Hyperbolic Spaces.
LDR:02578nmm a2200325 4500 001 2349850
005 20221010063638.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798544204398
035 $a (MiAaPQ)AAI28688401
035 $a (MiAaPQ)STANFORDbj040rx3340
035 $a AAI28688401
040 $a MiAaPQ $c MiAaPQ
100 1 $a Chami, Ines. $3 3689273
245 1 0 $a Representation Learning and Algorithms in Hyperbolic Spaces.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 193 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
500 $a Advisor: Re, Christopher.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Graph embedding methods aim at learning representations of nodes that preserve graph properties (e.g., graph distances). These embeddings can then be used in downstream applications such as clustering, visualization, nearest neighbor search and classification tasks. Most machine learning algorithms learn embeddings in standard Euclidean spaces. Recent research shows promise for more faithful embeddings by leveraging non-Euclidean geometries, such as hyperbolic or spherical geometries. In particular, trees can be embedded almost perfectly into two-dimensional hyperbolic spaces, while this is not possible in Euclidean spaces of any dimension. In this thesis, we develop machine learning models that operate in hyperbolic spaces. We start by introducing hyperbolic representation learning methods for hierarchical graphs, including methods for multi relational graphs or graphs with node features. We demonstrate the benefits of these hyperbolic representations compared to their Euclidean counterparts on a variety of link prediction benchmark datasets. We then design algorithms that operate on these hyperbolic representations. We first propose a method for hierarchical clustering in hyperbolic space, which can be used to solve any similarity-based hierarchical clustering problem with gradient-descent. We then propose a generalization of Principal Component Analysis for hyperbolic inputs, and show that it yields improved low-dimensional representations and data visualizations compared to previous manifold dimensionality reduction methods.
590 $a School code: 0212.
650 4 $a Taxonomy. $3 3556303
650 4 $a Algorithms. $3 536374
650 4 $a Geometry. $3 517251
650 4 $a Graph representations. $3 3560730
650 4 $a Neural networks. $3 677449
650 4 $a Mathematics. $3 515831
650 4 $a Artificial intelligence. $3 516317
650 4 $a Computer science. $3 523869
690 $a 0405
690 $a 0800
690 $a 0984
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-05B.
790 $a 0212
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28688401