TY - GEN
T1 - Homophily, structure, and content augmented network representation learning
AU - Zhang, Daokun
AU - Yin, Jie
AU - Zhu, Xingquan
AU - Zhang, Chengqi
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/7/2
Y1 - 2016/7/2
N2 - Advances in social networking and communication technologies have witnessed an increasing number of applications where data is not only characterized by rich content information, but also connected with complex relationships representing social roles and dependencies between individuals. To enable knowledge discovery from such networked data, network representation learning (NRL) aims to learn vector representations for network nodes, such that off-The-shelf machine learning algorithms can be directly applied. To date, existing NRL methods either primarily focus on network structure or simply combine node content and topology for learning. We argue that in information networks, information is mainly originated from three sources: (1) homophily, (2) topology structure, and (3) node content. Homophily states social phenomenon where individuals sharing similar attributes (content) tend to be directly connected through local relational ties, while topology structure emphasizes more on global connections. To ensure effective network representation learning, we propose to augment three information sources into one learning objective function, so that the interplay roles between three parties are enforced by requiring the learned network representations (1) being consistent with node content and topology structure, and also (2) following the social homophily constraints in the learned space. Experiments on multi-class node classification demonstrate that the representations learned by the proposed method consistently outperform state-of-The-Art NRL methods, especially for very sparsely labeled networks.
AB - Advances in social networking and communication technologies have witnessed an increasing number of applications where data is not only characterized by rich content information, but also connected with complex relationships representing social roles and dependencies between individuals. To enable knowledge discovery from such networked data, network representation learning (NRL) aims to learn vector representations for network nodes, such that off-The-shelf machine learning algorithms can be directly applied. To date, existing NRL methods either primarily focus on network structure or simply combine node content and topology for learning. We argue that in information networks, information is mainly originated from three sources: (1) homophily, (2) topology structure, and (3) node content. Homophily states social phenomenon where individuals sharing similar attributes (content) tend to be directly connected through local relational ties, while topology structure emphasizes more on global connections. To ensure effective network representation learning, we propose to augment three information sources into one learning objective function, so that the interplay roles between three parties are enforced by requiring the learned network representations (1) being consistent with node content and topology structure, and also (2) following the social homophily constraints in the learned space. Experiments on multi-class node classification demonstrate that the representations learned by the proposed method consistently outperform state-of-The-Art NRL methods, especially for very sparsely labeled networks.
UR - http://www.scopus.com/inward/record.url?scp=85014539437&partnerID=8YFLogxK
U2 - 10.1109/ICDM.2016.139
DO - 10.1109/ICDM.2016.139
M3 - Conference contribution
AN - SCOPUS:85014539437
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 609
EP - 618
BT - Proceedings - 16th IEEE International Conference on Data Mining, ICDM 2016
A2 - Bonchi, Francesco
A2 - Domingo-Ferrer, Josep
A2 - Baeza-Yates, Ricardo
A2 - Zhou, Zhi-Hua
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 16th IEEE International Conference on Data Mining, ICDM 2016
Y2 - 12 December 2016 through 15 December 2016
ER -