HEAT: Hyperbolic Embedding of Attributed Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Standard

HEAT: Hyperbolic Embedding of Attributed Networks. / McDonald, David; He, Shan.

Intelligent Data Engineering and Automated Learning, IDEAL 2020: 21st International Conference, Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 2020.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

McDonald, D & He, S 2020, HEAT: Hyperbolic Embedding of Attributed Networks. in Intelligent Data Engineering and Automated Learning, IDEAL 2020: 21st International Conference, Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 21st International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2020, Guimaraes, Portugal, 4/11/20.

APA

McDonald, D., & He, S. (Accepted/In press). HEAT: Hyperbolic Embedding of Attributed Networks. In Intelligent Data Engineering and Automated Learning, IDEAL 2020: 21st International Conference, Proceedings Institute of Electrical and Electronics Engineers (IEEE).

Vancouver

McDonald D, He S. HEAT: Hyperbolic Embedding of Attributed Networks. In Intelligent Data Engineering and Automated Learning, IDEAL 2020: 21st International Conference, Proceedings. Institute of Electrical and Electronics Engineers (IEEE). 2020

Author

McDonald, David ; He, Shan. / HEAT: Hyperbolic Embedding of Attributed Networks. Intelligent Data Engineering and Automated Learning, IDEAL 2020: 21st International Conference, Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 2020.

Bibtex

@inproceedings{220e6a0982b2427f877e5f1388301df6,
title = "HEAT: Hyperbolic Embedding of Attributed Networks",
abstract = "Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding networks into hyperbolic space because it can naturally represent a network's hierarchical structure. However, existing hyperbolic embedding approaches cannot deal with attributed networks, in which nodes are annotated with additional attributes. These attributes might provide additional proximity information to constrain the representations of the nodes, which is important to learn high quality hyperbolic embeddings. To overcome this gap we propose HEAT (Hyperbolic Embedding of Attributed Networks). HEAT first extracts training samples from the original graph capturing both topological and attribute similarity and then learns a hyperboloid embedding using full Riemannian Stochastic Gradient Descent. We show that HEAT can outperform other network embedding algorithms on several downstream tasks. As a general embedding method, HEAT opens the door to hyperbolic manifold learning on a wide range of attributed and unattributed networks.",
keywords = "Network embedding, Hyperbolic embedding, Random walk",
author = "David McDonald and Shan He",
year = "2020",
month = aug,
day = "5",
language = "English",
booktitle = "Intelligent Data Engineering and Automated Learning, IDEAL 2020",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
note = "21st International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2020 ; Conference date: 04-11-2020 Through 06-11-2020",

}

RIS

TY - GEN

T1 - HEAT: Hyperbolic Embedding of Attributed Networks

AU - McDonald, David

AU - He, Shan

PY - 2020/8/5

Y1 - 2020/8/5

N2 - Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding networks into hyperbolic space because it can naturally represent a network's hierarchical structure. However, existing hyperbolic embedding approaches cannot deal with attributed networks, in which nodes are annotated with additional attributes. These attributes might provide additional proximity information to constrain the representations of the nodes, which is important to learn high quality hyperbolic embeddings. To overcome this gap we propose HEAT (Hyperbolic Embedding of Attributed Networks). HEAT first extracts training samples from the original graph capturing both topological and attribute similarity and then learns a hyperboloid embedding using full Riemannian Stochastic Gradient Descent. We show that HEAT can outperform other network embedding algorithms on several downstream tasks. As a general embedding method, HEAT opens the door to hyperbolic manifold learning on a wide range of attributed and unattributed networks.

AB - Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding networks into hyperbolic space because it can naturally represent a network's hierarchical structure. However, existing hyperbolic embedding approaches cannot deal with attributed networks, in which nodes are annotated with additional attributes. These attributes might provide additional proximity information to constrain the representations of the nodes, which is important to learn high quality hyperbolic embeddings. To overcome this gap we propose HEAT (Hyperbolic Embedding of Attributed Networks). HEAT first extracts training samples from the original graph capturing both topological and attribute similarity and then learns a hyperboloid embedding using full Riemannian Stochastic Gradient Descent. We show that HEAT can outperform other network embedding algorithms on several downstream tasks. As a general embedding method, HEAT opens the door to hyperbolic manifold learning on a wide range of attributed and unattributed networks.

KW - Network embedding

KW - Hyperbolic embedding

KW - Random walk

M3 - Conference contribution

BT - Intelligent Data Engineering and Automated Learning, IDEAL 2020

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 21st International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2020

Y2 - 4 November 2020 through 6 November 2020

ER -