Abstract

Network embedding has gained more attentions in recent years. It has been shown that the learned low-dimensional node vector representations could advance a myriad of graph mining tasks such as node classification, community detection, and link prediction. A vast majority of the existing efforts are overwhelmingly devoted to single-layered networks or homogeneous networks with a single type of nodes and node interactions. However, in many real-world applications, a variety of networks could be abstracted and presented in a multi-layered fashion. Typical multi-layered networks include critical infrastructure systems, collaboration platforms, social recommender systems, to name a few. Despite the widespread use of multi-layered networks, it remains a daunting task to learn vector representations of different types of nodes due to the bewildering combination of both within-layer connections and cross-layer network dependencies. In this paper, we study a novel problem of multi-layered network embedding. In particular, we propose a principled framework-MANE to model both within-layer connections and cross-layer network dependencies simultaneously in a unified optimization framework for embedding representation learning. Experiments on real-world multi-layered networks corroborate the effectiveness of the proposed framework.

Original languageEnglish (US)
Pages684-692
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

Network layers
Critical infrastructures
Recommender systems
Experiments

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Li, J., Chen, C., Tong, H., & Liu, H. (2018). Multi-layered network embedding. 684-692. Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.

Multi-layered network embedding. / Li, Jundong; Chen, Chen; Tong, Hanghang; Liu, Huan.

2018. 684-692 Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.

Research output: Contribution to conferencePaper

Li, J, Chen, C, Tong, H & Liu, H 2018, 'Multi-layered network embedding' Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States, 5/3/18 - 5/5/18, pp. 684-692.
Li J, Chen C, Tong H, Liu H. Multi-layered network embedding. 2018. Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.
Li, Jundong ; Chen, Chen ; Tong, Hanghang ; Liu, Huan. / Multi-layered network embedding. Paper presented at 2018 SIAM International Conference on Data Mining, SDM 2018, San Diego, United States.9 p.
@conference{e73138f1aa334668a4d6cf633d98de07,
title = "Multi-layered network embedding",
abstract = "Network embedding has gained more attentions in recent years. It has been shown that the learned low-dimensional node vector representations could advance a myriad of graph mining tasks such as node classification, community detection, and link prediction. A vast majority of the existing efforts are overwhelmingly devoted to single-layered networks or homogeneous networks with a single type of nodes and node interactions. However, in many real-world applications, a variety of networks could be abstracted and presented in a multi-layered fashion. Typical multi-layered networks include critical infrastructure systems, collaboration platforms, social recommender systems, to name a few. Despite the widespread use of multi-layered networks, it remains a daunting task to learn vector representations of different types of nodes due to the bewildering combination of both within-layer connections and cross-layer network dependencies. In this paper, we study a novel problem of multi-layered network embedding. In particular, we propose a principled framework-MANE to model both within-layer connections and cross-layer network dependencies simultaneously in a unified optimization framework for embedding representation learning. Experiments on real-world multi-layered networks corroborate the effectiveness of the proposed framework.",
author = "Jundong Li and Chen Chen and Hanghang Tong and Huan Liu",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
pages = "684--692",
note = "2018 SIAM International Conference on Data Mining, SDM 2018 ; Conference date: 03-05-2018 Through 05-05-2018",

}

TY - CONF

T1 - Multi-layered network embedding

AU - Li, Jundong

AU - Chen, Chen

AU - Tong, Hanghang

AU - Liu, Huan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Network embedding has gained more attentions in recent years. It has been shown that the learned low-dimensional node vector representations could advance a myriad of graph mining tasks such as node classification, community detection, and link prediction. A vast majority of the existing efforts are overwhelmingly devoted to single-layered networks or homogeneous networks with a single type of nodes and node interactions. However, in many real-world applications, a variety of networks could be abstracted and presented in a multi-layered fashion. Typical multi-layered networks include critical infrastructure systems, collaboration platforms, social recommender systems, to name a few. Despite the widespread use of multi-layered networks, it remains a daunting task to learn vector representations of different types of nodes due to the bewildering combination of both within-layer connections and cross-layer network dependencies. In this paper, we study a novel problem of multi-layered network embedding. In particular, we propose a principled framework-MANE to model both within-layer connections and cross-layer network dependencies simultaneously in a unified optimization framework for embedding representation learning. Experiments on real-world multi-layered networks corroborate the effectiveness of the proposed framework.

AB - Network embedding has gained more attentions in recent years. It has been shown that the learned low-dimensional node vector representations could advance a myriad of graph mining tasks such as node classification, community detection, and link prediction. A vast majority of the existing efforts are overwhelmingly devoted to single-layered networks or homogeneous networks with a single type of nodes and node interactions. However, in many real-world applications, a variety of networks could be abstracted and presented in a multi-layered fashion. Typical multi-layered networks include critical infrastructure systems, collaboration platforms, social recommender systems, to name a few. Despite the widespread use of multi-layered networks, it remains a daunting task to learn vector representations of different types of nodes due to the bewildering combination of both within-layer connections and cross-layer network dependencies. In this paper, we study a novel problem of multi-layered network embedding. In particular, we propose a principled framework-MANE to model both within-layer connections and cross-layer network dependencies simultaneously in a unified optimization framework for embedding representation learning. Experiments on real-world multi-layered networks corroborate the effectiveness of the proposed framework.

UR - http://www.scopus.com/inward/record.url?scp=85048316063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048316063&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85048316063

SP - 684

EP - 692

ER -