TY - GEN
T1 - Multi-task network embedding
AU - Xu, Linchuan
AU - Wei, Xiaokai
AU - Cao, Jiannong
AU - Yu, Philip S.
PY - 2017/7/2
Y1 - 2017/7/2
N2 - As there are various data mining applications involving network analysis, network embedding is frequently employed to learn latent representations or embeddings that encode the network structure. However, existing network embedding models are only designed for a single network scenario. It is common that nodes can have multiple types of relationships in big data era, which results in multiple networks, e.g., multiple social networks and multiple gene regulatory networks. Jointly embedding multiple networks thus may make network-specific embeddings more comprehensive and complete as the same node may expose similar or complementary characteristics in different networks. In this paper, we thus propose an idea of multi-task network embedding (MTNE) to jointly learn multiple network-specific embeddings for each node via enforcing an extra information-sharing embedding. Moreover, we instantiate the idea in two models that are different in the mechanism for enforcing the information-sharing embedding. The first model enforces the information-sharing embedding as a common embedding shared by all tasks, which is similar to the concept of the common metric in multi-task metric learning while the second model enforces the information-sharing embedding as a consensus embedding on which all network-specific embeddings agree. We demonstrate through comprehensive experiments on three real-world datasets that the proposed models outperform state-of-the-art network embedding models in applications including visualization, link prediction, and multi-label classification.
AB - As there are various data mining applications involving network analysis, network embedding is frequently employed to learn latent representations or embeddings that encode the network structure. However, existing network embedding models are only designed for a single network scenario. It is common that nodes can have multiple types of relationships in big data era, which results in multiple networks, e.g., multiple social networks and multiple gene regulatory networks. Jointly embedding multiple networks thus may make network-specific embeddings more comprehensive and complete as the same node may expose similar or complementary characteristics in different networks. In this paper, we thus propose an idea of multi-task network embedding (MTNE) to jointly learn multiple network-specific embeddings for each node via enforcing an extra information-sharing embedding. Moreover, we instantiate the idea in two models that are different in the mechanism for enforcing the information-sharing embedding. The first model enforces the information-sharing embedding as a common embedding shared by all tasks, which is similar to the concept of the common metric in multi-task metric learning while the second model enforces the information-sharing embedding as a consensus embedding on which all network-specific embeddings agree. We demonstrate through comprehensive experiments on three real-world datasets that the proposed models outperform state-of-the-art network embedding models in applications including visualization, link prediction, and multi-label classification.
UR - http://www.scopus.com/inward/record.url?scp=85046256333&partnerID=8YFLogxK
U2 - 10.1109/DSAA.2017.19
DO - 10.1109/DSAA.2017.19
M3 - Conference article published in proceeding or book
AN - SCOPUS:85046256333
T3 - Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017
SP - 571
EP - 580
BT - Proceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th International Conference on Data Science and Advanced Analytics, DSAA 2017
Y2 - 19 October 2017 through 21 October 2017
ER -