ASPEM: Embedding learning by aspects in heterogeneous information networks

Yu Shi, Huan Gui, Qi Zhu, Lance Kaplan, Jiawei Han

Research output: Contribution to conferencePaper

Abstract

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.

Original languageEnglish (US)
Pages144-152
Number of pages9
StatePublished - Jan 1 2018
Event2018 SIAM International Conference on Data Mining, SDM 2018 - San Diego, United States
Duration: May 3 2018May 5 2018

Other

Other2018 SIAM International Conference on Data Mining, SDM 2018
CountryUnited States
CitySan Diego
Period5/3/185/5/18

Fingerprint

Semantics
Experiments
Statistics

Keywords

  • Graph mining
  • Heterogeneous information networks
  • Network embedding
  • Representation learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Shi, Y., Gui, H., Zhu, Q., Kaplan, L., & Han, J. (2018). ASPEM: Embedding learning by aspects in heterogeneous information networks. 144-152. Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.

ASPEM : Embedding learning by aspects in heterogeneous information networks. / Shi, Yu; Gui, Huan; Zhu, Qi; Kaplan, Lance; Han, Jiawei.

2018. 144-152 Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.

Research output: Contribution to conferencePaper

Shi, Y, Gui, H, Zhu, Q, Kaplan, L & Han, J 2018, 'ASPEM: Embedding learning by aspects in heterogeneous information networks' Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States, 5/3/18 - 5/5/18, pp. 144-152.
Shi Y, Gui H, Zhu Q, Kaplan L, Han J. ASPEM: Embedding learning by aspects in heterogeneous information networks. 2018. Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.
Shi, Yu ; Gui, Huan ; Zhu, Qi ; Kaplan, Lance ; Han, Jiawei. / ASPEM : Embedding learning by aspects in heterogeneous information networks. Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.9 p.
@conference{d9fbfbad40c946b49a93fe7ae05f4984,
title = "ASPEM: Embedding learning by aspects in heterogeneous information networks",
abstract = "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.",
keywords = "Graph mining, Heterogeneous information networks, Network embedding, Representation learning",
author = "Yu Shi and Huan Gui and Qi Zhu and Lance Kaplan and Jiawei Han",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
pages = "144--152",
note = "2018 SIAM International Conference on Data Mining, SDM 2018 ; Conference date: 03-05-2018 Through 05-05-2018",

}

TY - CONF

T1 - ASPEM

T2 - Embedding learning by aspects in heterogeneous information networks

AU - Shi, Yu

AU - Gui, Huan

AU - Zhu, Qi

AU - Kaplan, Lance

AU - Han, Jiawei

PY - 2018/1/1

Y1 - 2018/1/1

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

M3 - Paper

AN - SCOPUS:85048335897

SP - 144

EP - 152

ER -