• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Ksenia Korovina
Graph Embeddings for Multi-class Classification of Nodes and Edges
Mathematics
(Bachelor’s programme)
2018
Representing complicated combinatorial structures like graphs as vector embeddings in low-dimensional vector spaces is a challenging task of substantial practical significance in a range of domains, from recommender systems to biomedical analysis. It is also an emerging field with recent developments in the past few years, where a lot is to be investigated.

Our contribution with this work is two-fold. First, we provide an extensive study of modern machine learning methods for graph embeddings: their theoretical underpinnings as well as practical capabilities and limitations. Second, we propose a model we call DuoGAE, which learns node representations consistent with dual information by jointly embedding nodes and edges in common space. Experimental results show that the model outperforms state-of-the-art in terms of multiple quality measures on link prediction and node classification.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses