Skip to content. | Skip to navigation

Personal tools
You are here: Home Theses Including Attributes in a Graph Embedding


Prof. Dr. S. Decker
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports





Including Attributes in a Graph Embedding

Thesis type
  • Bachelor
  • Master
Student Jerome Lenssen
Status Finished
Submitted in 2018
Presentation on 19. Oct 2018 10:00
Presentation room Seminarraum I5
Add presentation to calendar vCal
File download

Lately several methods for embedding graphs nodes into a vector space have been proposed. These embeddings can then used to train other machine learning models. Most approaches will, however, only keep relations between nodes representing entities in the graph into account. If the graph also has nodes representing literal values (numbers, strings, etc.) then they are ignored. In this thesis, the student will investigate how these attributes can be included in the embedding.

Document Actions