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

Augmenting Structure with Text for Improved Graph Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Augmenting Structure with Text for Improved Graph Learning./
作者:	Safavi, Tara L.
面頁冊數:	1 online resource (186 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-04, Section: A.
Contained By:	Dissertations Abstracts International84-04A.
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29730444click for full text (PQDT)
ISBN:	9798845468840

Augmenting Structure with Text for Improved Graph Learning.
Safavi, Tara L.

Augmenting Structure with Text for Improved Graph Learning. - 1 online resource (186 pages)

Source: Dissertations Abstracts International, Volume: 84-04, Section: A.

Thesis (Ph.D.)--University of Michigan, 2022.

Includes bibliographical references

Many important problems in machine learning and data mining, such as knowledge base reasoning, personalized entity recommendation, and scientific hypothesis generation, may be framed as learning and inference over a graph data structure. Such problems represent exciting opportunities for advancing graph learning, but also entail significant challenges. Because graphs are typically sparse and defined by a schema, they often do not fully capture the underlying complex relationships in the data. Models that combine graphs with rich auxiliary textual modalities have higher potential for expressiveness, but jointly processing such disparate modalities - that is, sparse structured relations and dense unstructured text - is not straightforward.In this thesis, we consider the important problem of improving graph learning by combining structure and text. The first part of the thesis considers relational knowledge representation and reasoning tasks, demonstrating the great potential of pretrained contextual language models to add renewed depth and richness to graph-structured knowledge bases. The second part of the thesis goes beyond knowledge bases, toward improving graph learning tasks that arise in information retrieval and recommender systems by jointly modeling document interactions and content. Our proposed methodologies consistently improve accuracy over both single-modality and cross-modality baselines, suggesting that, with appropriately chosen inductive biases and careful model design, we can exploit the unique complementary aspects of structure and text to great effect.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798845468840Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Text-augmented graph learningIndex Terms--Genre/Form:

542853
Electronic books.

Augmenting Structure with Text for Improved Graph Learning.
LDR:03056nmm a2200433K 4500 001 2358360
005 20230731112628.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798845468840
035 $a (MiAaPQ)AAI29730444
035 $a (MiAaPQ)umichrackham004546
035 $a AAI29730444
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Safavi, Tara L. $3 3698895
245 1 0 $a Augmenting Structure with Text for Improved Graph Learning.
264 0 $c 2022
300 $a 1 online resource (186 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-04, Section: A.
500 $a Advisor: Koutra, Danai.
502 $a Thesis (Ph.D.)--University of Michigan, 2022.
504 $a Includes bibliographical references
520 $a Many important problems in machine learning and data mining, such as knowledge base reasoning, personalized entity recommendation, and scientific hypothesis generation, may be framed as learning and inference over a graph data structure. Such problems represent exciting opportunities for advancing graph learning, but also entail significant challenges. Because graphs are typically sparse and defined by a schema, they often do not fully capture the underlying complex relationships in the data. Models that combine graphs with rich auxiliary textual modalities have higher potential for expressiveness, but jointly processing such disparate modalities - that is, sparse structured relations and dense unstructured text - is not straightforward.In this thesis, we consider the important problem of improving graph learning by combining structure and text. The first part of the thesis considers relational knowledge representation and reasoning tasks, demonstrating the great potential of pretrained contextual language models to add renewed depth and richness to graph-structured knowledge bases. The second part of the thesis goes beyond knowledge bases, toward improving graph learning tasks that arise in information retrieval and recommender systems by jointly modeling document interactions and content. Our proposed methodologies consistently improve accuracy over both single-modality and cross-modality baselines, suggesting that, with appropriately chosen inductive biases and careful model design, we can exploit the unique complementary aspects of structure and text to great effect.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Epistemology. $3 896969
650 4 $a Information science. $3 554358
653 $a Text-augmented graph learning
653 $a Knowledge representation
653 $a Content mining
653 $a Machine learning
653 $a Reasoning
653 $a Graph data
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0984
690 $a 0393
690 $a 0723
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Michigan. $b Computer Science & Engineering. $3 3285590
773 0 $t Dissertations Abstracts International $g 84-04A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29730444 $z click for full text (PQDT)