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

Overlapping communities detection in network

Student: Anna Yaushkina

Supervisor: Alexander Ponomarenko

Faculty: Faculty of Informatics, Mathematics, and Computer Science (HSE Nizhny Novgorod)

Educational Programme: Data Mining (Master)

Year of Graduation: 2018

Overlapped community search in networks is a clusterization problem where communities are represented by (possibly overlapped) clusters. This paper studies an algorithm based on an idea of Partitioning Around Medoids that utilizes solution to P-median problem to determine cluster center in line graph. Since clustering is performed on the edges of the graph, it allows to identify vertices that belong to multiple clusters. We propose to replace Commute Distance used in the algorithm with Amplified Commute Distance. Also we present a way to improve clustering speed of the algorithm by using CLARANS instead of P-median problem-based edge clustering. Experiments on real and random data shoow that new distance measure in combination with edge modified clustering show both better runtime and resulting cluster quality.

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