Graph Representation Learning and Its Applications: A Survey
Graphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/8/4168 |
| _version_ | 1797603404516687872 |
|---|---|
| author | Van Thuy Hoang Hyeon-Ju Jeon Eun-Soon You Yoewon Yoon Sungyeop Jung O-Joun Lee |
| author_facet | Van Thuy Hoang Hyeon-Ju Jeon Eun-Soon You Yoewon Yoon Sungyeop Jung O-Joun Lee |
| author_sort | Van Thuy Hoang |
| collection | DOAJ |
| description | Graphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities to low-dimensional vectors while preserving graph structure and entity relationships. Over the decades, many models have been proposed for graph representation learning. This paper aims to show a comprehensive picture of graph representation learning models, including traditional and state-of-the-art models on various graphs in different geometric spaces. First, we begin with five types of graph embedding models: graph kernels, matrix factorization models, shallow models, deep-learning models, and non-Euclidean models. In addition, we also discuss graph transformer models and Gaussian embedding models. Second, we present practical applications of graph embedding models, from constructing graphs for specific domains to applying models to solve tasks. Finally, we discuss challenges for existing models and future research directions in detail. As a result, this paper provides a structured overview of the diversity of graph embedding models. |
| first_indexed | 2024-03-11T04:31:40Z |
| format | Article |
| id | doaj.art-0f3289eb6e7d45a7ab3776d099a56b06 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:31:40Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0f3289eb6e7d45a7ab3776d099a56b062023-11-17T21:20:01ZengMDPI AGSensors1424-82202023-04-01238416810.3390/s23084168Graph Representation Learning and Its Applications: A SurveyVan Thuy Hoang0Hyeon-Ju Jeon1Eun-Soon You2Yoewon Yoon3Sungyeop Jung4O-Joun Lee5Department of Artificial Intelligence, The Catholic University of Korea, 43, Jibong-ro, Bucheon-si 14662, Gyeonggi-do, Republic of KoreaData Assimilation Group, Korea Institute of Atmospheric Prediction Systems (KIAPS), 35, Boramae-ro 5-gil, Dongjak-gu, Seoul 07071, Republic of KoreaDepartment of Artificial Intelligence, The Catholic University of Korea, 43, Jibong-ro, Bucheon-si 14662, Gyeonggi-do, Republic of KoreaDepartment of Social Welfare, Dongguk University, 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaSemiconductor Devices and Circuits Laboratory, Advanced Institute of Convergence Technology (AICT), Seoul National University, 145, Gwanggyo-ro, Yeongtong-gu, Suwon-si 16229, Gyeonggi-do, Republic of KoreaDepartment of Artificial Intelligence, The Catholic University of Korea, 43, Jibong-ro, Bucheon-si 14662, Gyeonggi-do, Republic of KoreaGraphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities to low-dimensional vectors while preserving graph structure and entity relationships. Over the decades, many models have been proposed for graph representation learning. This paper aims to show a comprehensive picture of graph representation learning models, including traditional and state-of-the-art models on various graphs in different geometric spaces. First, we begin with five types of graph embedding models: graph kernels, matrix factorization models, shallow models, deep-learning models, and non-Euclidean models. In addition, we also discuss graph transformer models and Gaussian embedding models. Second, we present practical applications of graph embedding models, from constructing graphs for specific domains to applying models to solve tasks. Finally, we discuss challenges for existing models and future research directions in detail. As a result, this paper provides a structured overview of the diversity of graph embedding models.https://www.mdpi.com/1424-8220/23/8/4168graph embeddinggraph representation learninggraph transformergraph neural networks |
| spellingShingle | Van Thuy Hoang Hyeon-Ju Jeon Eun-Soon You Yoewon Yoon Sungyeop Jung O-Joun Lee Graph Representation Learning and Its Applications: A Survey Sensors graph embedding graph representation learning graph transformer graph neural networks |
| title | Graph Representation Learning and Its Applications: A Survey |
| title_full | Graph Representation Learning and Its Applications: A Survey |
| title_fullStr | Graph Representation Learning and Its Applications: A Survey |
| title_full_unstemmed | Graph Representation Learning and Its Applications: A Survey |
| title_short | Graph Representation Learning and Its Applications: A Survey |
| title_sort | graph representation learning and its applications a survey |
| topic | graph embedding graph representation learning graph transformer graph neural networks |
| url | https://www.mdpi.com/1424-8220/23/8/4168 |
| work_keys_str_mv | AT vanthuyhoang graphrepresentationlearninganditsapplicationsasurvey AT hyeonjujeon graphrepresentationlearninganditsapplicationsasurvey AT eunsoonyou graphrepresentationlearninganditsapplicationsasurvey AT yoewonyoon graphrepresentationlearninganditsapplicationsasurvey AT sungyeopjung graphrepresentationlearninganditsapplicationsasurvey AT ojounlee graphrepresentationlearninganditsapplicationsasurvey |