TY - CONF
T1 - ASPEM
T2 - 2018 SIAM International Conference on Data Mining, SDM 2018
AU - Shi, Yu
AU - Gui, Huan
AU - Zhu, Qi
AU - Kaplan, Lance
AU - Han, Jiawei
N1 - Funding Information:
This work was partially funded by the Office of Naval Research under contract N00014-16-C-1054 and by the U.S. Department of Homeland Security under Grant Award Number 2017-ST-061-CINA01. The views and conclusions contained in this document are those of the authors and should not be interpreted as necessarily representing the official policies, either expressed or implied, of the Office of Naval Research or the U.S. Department of Homeland Security.
PY - 2018
Y1 - 2018
N2 - Heterogeneous information networks (HINs) are ubiquitous in real-world applications. Due to the heterogeneity in HINs, the typed edges may not fully align with each other. In order to capture the semantic subtlety, we propose the concept of aspects with each aspect being a unit representing one underlying semantic facet. Meanwhile, network embedding has emerged as a powerful method for learning network representation, where the learned embedding can be used as features in various downstream applications. Therefore, we are motivated to propose a novel embedding learning framework-ASPEM-to preserve the semantic information in HINs based on multiple aspects. Instead of preserving information of the network in one semantic space, ASPEM encapsulates information regarding each aspect individually. In order to select aspects for embedding purpose, we further devise a solution for ASPEM based on datasetwide statistics. To corroborate the efficacy of ASPEM, we conducted experiments on two real-words datasets with two types of applications-classification and link prediction. Experiment results demonstrate that ASPEM can outperform baseline network embedding learning methods by considering multiple aspects, where the aspects can be selected from the given HIN in an unsupervised manner.
AB - Heterogeneous information networks (HINs) are ubiquitous in real-world applications. Due to the heterogeneity in HINs, the typed edges may not fully align with each other. In order to capture the semantic subtlety, we propose the concept of aspects with each aspect being a unit representing one underlying semantic facet. Meanwhile, network embedding has emerged as a powerful method for learning network representation, where the learned embedding can be used as features in various downstream applications. Therefore, we are motivated to propose a novel embedding learning framework-ASPEM-to preserve the semantic information in HINs based on multiple aspects. Instead of preserving information of the network in one semantic space, ASPEM encapsulates information regarding each aspect individually. In order to select aspects for embedding purpose, we further devise a solution for ASPEM based on datasetwide statistics. To corroborate the efficacy of ASPEM, we conducted experiments on two real-words datasets with two types of applications-classification and link prediction. Experiment results demonstrate that ASPEM can outperform baseline network embedding learning methods by considering multiple aspects, where the aspects can be selected from the given HIN in an unsupervised manner.
KW - Graph mining
KW - Heterogeneous information networks
KW - Network embedding
KW - Representation learning
UR - http://www.scopus.com/inward/record.url?scp=85048335897&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048335897&partnerID=8YFLogxK
U2 - 10.1137/1.9781611975321.16
DO - 10.1137/1.9781611975321.16
M3 - Paper
AN - SCOPUS:85048335897
SP - 144
EP - 152
Y2 - 3 May 2018 through 5 May 2018
ER -