Neural Architecture Search in Recommender Systems

Student: Bashkirov Danil

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2021

This work is devoted to methods of searching for neural network architectures using recommender systems as an example. The paper discusses various types of recommender systems and ways to automate them. Efficiency assessment is based on comparing the results obtained from models built with NAS and without it. Based on the results of the study, an analysis was carried out, which shows that recommender systems built using NAS are superior in quality to systems built without looking for neural network architectures.

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