HEAT: Hyperbolic Embedding of Attributed Networks
Research output: Chapter in Book/Report/Conference proceeding › Conference 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 proceeding › Conference contribution
Harvard
APA
Vancouver
Author
Bibtex
}
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 -