A Brief Review of Network Embedding
Learning the representations of nodes in a network can benefit various analysis tasks such as node classification, link prediction, clustering, and anomaly detection. Such a representation learning problem is referred to as network embedding, and it has attracted significant attention in recent year...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2019-03-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2018.9020029 |
| _version_ | 1811250934145089536 |
|---|---|
| author | Yaojing Wang Yuan Yao Hanghang Tong Feng Xu Jian Lu |
| author_facet | Yaojing Wang Yuan Yao Hanghang Tong Feng Xu Jian Lu |
| author_sort | Yaojing Wang |
| collection | DOAJ |
| description | Learning the representations of nodes in a network can benefit various analysis tasks such as node classification, link prediction, clustering, and anomaly detection. Such a representation learning problem is referred to as network embedding, and it has attracted significant attention in recent years. In this article, we briefly review the existing network embedding methods by two taxonomies. The technical taxonomy focuses on the specific techniques used and divides the existing network embedding methods into two stages, i.e., context construction and objective design. The non-technical taxonomy focuses on the problem setting aspect and categorizes existing work based on whether to preserve special network properties, to consider special network types, or to incorporate additional inputs. Finally, we summarize the main findings based on the two taxonomies, analyze their usefulness, and discuss future directions in this area. |
| first_indexed | 2024-04-12T16:12:12Z |
| format | Article |
| id | doaj.art-cafcb4edf5924a19b5c2bd0e26abe500 |
| institution | Directory Open Access Journal |
| issn | 2096-0654 |
| language | English |
| last_indexed | 2024-04-12T16:12:12Z |
| publishDate | 2019-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj.art-cafcb4edf5924a19b5c2bd0e26abe5002022-12-22T03:25:52ZengTsinghua University PressBig Data Mining and Analytics2096-06542019-03-0121354710.26599/BDMA.2018.9020029A Brief Review of Network EmbeddingYaojing Wang0Yuan Yao1Hanghang Tong2Feng Xu3Jian Lu4<institution content-type="dept">State Key Laboratory for Novel Software Technology</institution> <institution>Nanjing University</institution>, <city>Nanjing</city> <postal-code>210023</postal-code>, <country>China</country>.<institution content-type="dept">State Key Laboratory for Novel Software Technology</institution> <institution>Nanjing University</institution>, <city>Nanjing</city> <postal-code>210023</postal-code>, <country>China</country>.<institution content-type="dept">School of Computing, Informatics and Decision Systems Engineering</institution>, <institution>Arizona State University</institution>, <state>AZ</state> <postal-code>85281</postal-code>, <country>USA</country>.<institution content-type="dept">State Key Laboratory for Novel Software Technology</institution> <institution>Nanjing University</institution>, <city>Nanjing</city> <postal-code>210023</postal-code>, <country>China</country>.<institution content-type="dept">State Key Laboratory for Novel Software Technology</institution> <institution>Nanjing University</institution>, <city>Nanjing</city> <postal-code>210023</postal-code>, <country>China</country>.Learning the representations of nodes in a network can benefit various analysis tasks such as node classification, link prediction, clustering, and anomaly detection. Such a representation learning problem is referred to as network embedding, and it has attracted significant attention in recent years. In this article, we briefly review the existing network embedding methods by two taxonomies. The technical taxonomy focuses on the specific techniques used and divides the existing network embedding methods into two stages, i.e., context construction and objective design. The non-technical taxonomy focuses on the problem setting aspect and categorizes existing work based on whether to preserve special network properties, to consider special network types, or to incorporate additional inputs. Finally, we summarize the main findings based on the two taxonomies, analyze their usefulness, and discuss future directions in this area.https://www.sciopen.com/article/10.26599/BDMA.2018.9020029network embeddingnode representationscontext construction |
| spellingShingle | Yaojing Wang Yuan Yao Hanghang Tong Feng Xu Jian Lu A Brief Review of Network Embedding Big Data Mining and Analytics network embedding node representations context construction |
| title | A Brief Review of Network Embedding |
| title_full | A Brief Review of Network Embedding |
| title_fullStr | A Brief Review of Network Embedding |
| title_full_unstemmed | A Brief Review of Network Embedding |
| title_short | A Brief Review of Network Embedding |
| title_sort | brief review of network embedding |
| topic | network embedding node representations context construction |
| url | https://www.sciopen.com/article/10.26599/BDMA.2018.9020029 |
| work_keys_str_mv | AT yaojingwang abriefreviewofnetworkembedding AT yuanyao abriefreviewofnetworkembedding AT hanghangtong abriefreviewofnetworkembedding AT fengxu abriefreviewofnetworkembedding AT jianlu abriefreviewofnetworkembedding AT yaojingwang briefreviewofnetworkembedding AT yuanyao briefreviewofnetworkembedding AT hanghangtong briefreviewofnetworkembedding AT fengxu briefreviewofnetworkembedding AT jianlu briefreviewofnetworkembedding |