Abstract
Real-world social networks and digital platforms are comprised of individuals (nodes) that are linked to other individuals or entities through multiple types of relationships (links). Sub-networks of such a network based on each type of link correspond to distinct views of the underlying network. In real-world applications each node is typically linked to only a small subset of other nodes. Hence, practical approaches to problems such as node labeling have to cope with the resulting sparse networks. While low-dimensional network embeddings offer a promising approach to this problem, most of the current network embedding methods focus primarily on single view networks. We introduce a novel multi-view network embedding (MVNE) algorithm for constructing low-dimensional node embeddings from multi-view networks. MVNE adapts and extends an approach to single view node embedding using graph factorization clustering (GFC) to the multi-view setting using an objective function that maximizes the agreement between views based on both the local and global structure of the underlying multi-view graph. Our experiments with several benchmark real-world single view networks show that SVNE yields network embeddings that are competitive with or superior to those produced by the state-of-the-art single view network embedding methods when the embeddings are used for labeling unlabeled nodes in the networks. Our experiments with several multi-view networks show that MVNE substantially outperforms the single view methods on integrated view and the state-of-the-art multi-view methods. We further show that even when the goal is to predict labels of nodes within a single target view, MVNE outperforms its single-view counterpart suggesting that the MVNE is able to extract the information that is useful for labeling nodes in the target view from the all of the views.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 |
| Editors | Zhenhui Li, Hanghang Tong, Feida Zhu, Jeffrey Yu |
| Publisher | IEEE Computer Society |
| Pages | 1006-1013 |
| Number of pages | 8 |
| ISBN (Electronic) | 9781538692882 |
| DOIs | |
| State | Published - Feb 7 2019 |
| Event | 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 - Singapore, Singapore Duration: Nov 17 2018 → Nov 20 2018 |
Publication series
| Name | IEEE International Conference on Data Mining Workshops, ICDMW |
|---|---|
| Volume | 2018-November |
| ISSN (Print) | 2375-9232 |
| ISSN (Electronic) | 2375-9259 |
Conference
| Conference | 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018 |
|---|---|
| Country | Singapore |
| City | Singapore |
| Period | 11/17/18 → 11/20/18 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Software
Cite this
}
Multi-view network embedding via graph factorization clustering and co-regularized multi-view agreement. / Sun, Yiwei; Bui, Ngot; Hsieh, Tsung Yu; Honavar, Vasant.
Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018. ed. / Zhenhui Li; Hanghang Tong; Feida Zhu; Jeffrey Yu. IEEE Computer Society, 2019. p. 1006-1013 8637384 (IEEE International Conference on Data Mining Workshops, ICDMW; Vol. 2018-November).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Multi-view network embedding via graph factorization clustering and co-regularized multi-view agreement
AU - Sun, Yiwei
AU - Bui, Ngot
AU - Hsieh, Tsung Yu
AU - Honavar, Vasant
PY - 2019/2/7
Y1 - 2019/2/7
N2 - Real-world social networks and digital platforms are comprised of individuals (nodes) that are linked to other individuals or entities through multiple types of relationships (links). Sub-networks of such a network based on each type of link correspond to distinct views of the underlying network. In real-world applications each node is typically linked to only a small subset of other nodes. Hence, practical approaches to problems such as node labeling have to cope with the resulting sparse networks. While low-dimensional network embeddings offer a promising approach to this problem, most of the current network embedding methods focus primarily on single view networks. We introduce a novel multi-view network embedding (MVNE) algorithm for constructing low-dimensional node embeddings from multi-view networks. MVNE adapts and extends an approach to single view node embedding using graph factorization clustering (GFC) to the multi-view setting using an objective function that maximizes the agreement between views based on both the local and global structure of the underlying multi-view graph. Our experiments with several benchmark real-world single view networks show that SVNE yields network embeddings that are competitive with or superior to those produced by the state-of-the-art single view network embedding methods when the embeddings are used for labeling unlabeled nodes in the networks. Our experiments with several multi-view networks show that MVNE substantially outperforms the single view methods on integrated view and the state-of-the-art multi-view methods. We further show that even when the goal is to predict labels of nodes within a single target view, MVNE outperforms its single-view counterpart suggesting that the MVNE is able to extract the information that is useful for labeling nodes in the target view from the all of the views.
AB - Real-world social networks and digital platforms are comprised of individuals (nodes) that are linked to other individuals or entities through multiple types of relationships (links). Sub-networks of such a network based on each type of link correspond to distinct views of the underlying network. In real-world applications each node is typically linked to only a small subset of other nodes. Hence, practical approaches to problems such as node labeling have to cope with the resulting sparse networks. While low-dimensional network embeddings offer a promising approach to this problem, most of the current network embedding methods focus primarily on single view networks. We introduce a novel multi-view network embedding (MVNE) algorithm for constructing low-dimensional node embeddings from multi-view networks. MVNE adapts and extends an approach to single view node embedding using graph factorization clustering (GFC) to the multi-view setting using an objective function that maximizes the agreement between views based on both the local and global structure of the underlying multi-view graph. Our experiments with several benchmark real-world single view networks show that SVNE yields network embeddings that are competitive with or superior to those produced by the state-of-the-art single view network embedding methods when the embeddings are used for labeling unlabeled nodes in the networks. Our experiments with several multi-view networks show that MVNE substantially outperforms the single view methods on integrated view and the state-of-the-art multi-view methods. We further show that even when the goal is to predict labels of nodes within a single target view, MVNE outperforms its single-view counterpart suggesting that the MVNE is able to extract the information that is useful for labeling nodes in the target view from the all of the views.
UR - http://www.scopus.com/inward/record.url?scp=85062818085&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062818085&partnerID=8YFLogxK
U2 - 10.1109/ICDMW.2018.00145
DO - 10.1109/ICDMW.2018.00145
M3 - Conference contribution
AN - SCOPUS:85062818085
T3 - IEEE International Conference on Data Mining Workshops, ICDMW
SP - 1006
EP - 1013
BT - Proceedings - 18th IEEE International Conference on Data Mining Workshops, ICDMW 2018
A2 - Li, Zhenhui
A2 - Tong, Hanghang
A2 - Zhu, Feida
A2 - Yu, Jeffrey
PB - IEEE Computer Society
ER -