TY - GEN
T1 - Marine
T2 - 2019 World Wide Web Conference, WWW 2019
AU - Feng, Ming Han
AU - Hsu, Chin Chi
AU - Li, Cheng Te
AU - Yeh, Mi Yen
AU - Lin, Shou De
N1 - Funding Information:
This work is supported by Ministry of Science and Technology (MOST) of Taiwan under grants 108-2636-E-006-002, 107-2218-E-006-040, 107-2221-E-001-009-MY3, and 106-3114-E-002-008, by Air Force Office of Scientific Research and Asian Office of Aerospace Research and Development (AOARD) under award number FA2386-17-1-4038, and also by Academia Sinica under grant AS-TP-107-M05.
Publisher Copyright:
© 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License.
PY - 2019/5/13
Y1 - 2019/5/13
N2 - Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.
AB - Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.
UR - http://www.scopus.com/inward/record.url?scp=85066903914&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066903914&partnerID=8YFLogxK
U2 - 10.1145/3308558.3313715
DO - 10.1145/3308558.3313715
M3 - Conference contribution
AN - SCOPUS:85066903914
T3 - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
SP - 470
EP - 479
BT - The Web Conference 2019 - Proceedings of the World Wide Web Conference, WWW 2019
PB - Association for Computing Machinery, Inc
Y2 - 13 May 2019 through 17 May 2019
ER -