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

Temporal Learning for Dynamic Graph.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Temporal Learning for Dynamic Graph./
作者:	Zhu, Yue Cai.
面頁冊數:	1 online resource (101 pages)
附註:	Source: Masters Abstracts International, Volume: 85-01.
Contained By:	Masters Abstracts International85-01.
標題:	Taxonomy. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30548781click for full text (PQDT)
ISBN:	9798379872632

Temporal Learning for Dynamic Graph.
Zhu, Yue Cai.

Temporal Learning for Dynamic Graph. - 1 online resource (101 pages)

Source: Masters Abstracts International, Volume: 85-01.

Thesis (M.Sc.)--McGill University (Canada), 2022.

Includes bibliographical references

A graph is a data structure to model a complex system of entities connected in a particular relation. These entities are nodes in the graph, and the connections are edges. A dynamic graph is a graph that evolves in its nodes, edges or both. We can use it to analyze networks that are not static, such as social networks, academic citation networks and city traffic networks. The dynamic graph is a widely used data structure in various domains. However, the exploration of machine learning with dynamic graphs is still in its early stage. What are the drivers of a dynamic graph's evolution? How can we learn the temporal information from a dynamic graph's history? How can we determine if we should use dynamic graph learning algorithms to analyze a given graph? These are still open questions that are well worth to explore. In this thesis, I try to address the research questions above by a survey of recently developed supervised dynamic graph learning algorithms and proposing a dynamic graph temporal learning framework. Based on the framework above, I conducted an initial study on measuring the significance of temporal patterns to prepare for the research in predicting performance gain from dynamic graph learning algorithms.

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

Mode of access: World Wide Web

ISBN: 9798379872632Subjects--Topical Terms:

3556303
Taxonomy.
Index Terms--Genre/Form:

542853
Electronic books.

Temporal Learning for Dynamic Graph.
LDR:04008nmm a2200349K 4500 001 2364844
005 20231212064435.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798379872632
035 $a (MiAaPQ)AAI30548781
035 $a (MiAaPQ)McGill_cz30pz86f
035 $a AAI30548781
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Zhu, Yue Cai. $3 3705667
245 1 0 $a Temporal Learning for Dynamic Graph.
264 0 $c 2022
300 $a 1 online resource (101 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: Masters Abstracts International, Volume: 85-01.
500 $a Advisor: Liu, Xue.
502 $a Thesis (M.Sc.)--McGill University (Canada), 2022.
504 $a Includes bibliographical references
520 $a A graph is a data structure to model a complex system of entities connected in a particular relation. These entities are nodes in the graph, and the connections are edges. A dynamic graph is a graph that evolves in its nodes, edges or both. We can use it to analyze networks that are not static, such as social networks, academic citation networks and city traffic networks. The dynamic graph is a widely used data structure in various domains. However, the exploration of machine learning with dynamic graphs is still in its early stage. What are the drivers of a dynamic graph's evolution? How can we learn the temporal information from a dynamic graph's history? How can we determine if we should use dynamic graph learning algorithms to analyze a given graph? These are still open questions that are well worth to explore. In this thesis, I try to address the research questions above by a survey of recently developed supervised dynamic graph learning algorithms and proposing a dynamic graph temporal learning framework. Based on the framework above, I conducted an initial study on measuring the significance of temporal patterns to prepare for the research in predicting performance gain from dynamic graph learning algorithms.
520 $a Le graphe est une structure de donnees pour modeliser un systeme complexe d'entites qui sont connectees les unes aux autres dans un certain type de relation. Ces entites sont des sommets dans le graphe et les connexions sont des aretes. Un graphe dynamique est un graphe qui evolue dans le temps, dans ses sommets, ses aretes ou les deux. On peut l'utilise pour analyser les reseaux qui ne sont pas statiques. tels que les reseaux sociaux. les reseaux de citations universitaires et le reseau de trafic urbain. Le graphe dynamique est une structure de donnees largement utilisee dans domaines divers. Cependant. l'exploration de l'apprentissage automatique avec la graphe dynamique est encore A ses debuts. Quels sont les moteurs de l'evolution d'un graphe dynamique? Comment pouvons-nous apprendre les informations temporelles a partir de l'historique d'un graphe dynamique ? Comment determiner si nous devons utiliser des algorithmes d'apprentissage de graphes dynamique pour analyser un graphe? Ce sont encore des questions ouvertes qui bien meritent a explorer. Dans cette these, j'essaie de repondre les questions de recherche susmentionnees per une enquete sur les algorithmes d'apprentissage supervise de graphes dynamique recemment developpes, et proposer un cadre d'apprentissage temporel de graphe dynamique. Base sur le cadre d'apprentissage temporel mentionne, j'ai fait une etude prealable sur la mesure de la signification des modifs temporels, et me preparer a la recherche sur la prediction du gain de performance offert par les algorithmes d'apprentissage de graphes dynamique.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Taxonomy. $3 3556303
650 4 $a Graph representations. $3 3560730
650 4 $a Neural networks. $3 677449
650 4 $a Web studies. $3 2122754
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0646
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a McGill University (Canada). $3 1018122
773 0 $t Masters Abstracts International $g 85-01.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30548781 $z click for full text (PQDT)