November 2017
PhD student
Institute of Software Systems of NAS of Ukraine and National University of Kyiv Mohyla Academy
Kyiv, Ukraine
July - November 2016
IBM Research
Internship. Research topic: Predictive Caching & Cognitive Storage
Zurich, Switzerland
September 2015 - June 2017
Master Degree in Information Control Systems and Technologies
National University of Kyiv Mohyla Academy
Kyiv, Ukraine
Summer 2014
International Research-Centered Summer School (IRSS) in Cognitive Systems and Interactive Robotics, Data and Content Analysis
National Center For Scientific Research — Demokritos
Athens, Greece
September 2013 - June 2014
Bachelor exchange mobility, Erasmus Mundus Project ALRAKIS II
Tallinn University
Tallinn, Estonia
September 2010 - June 2015
Bachelor Degree in Applied Mathematics
National University of Kyiv Mohyla Academy
Kyiv, Ukraine

Publications

Thumbnail of Graph-Based Data Relevance Estimation for Large Storage Systems

Graph-Based Data Relevance Estimation for Large Storage Systems

Vinodh Venkatesan, Taras Lehinevych, Giovanni Cherubini, Andrii Glybovets, and Mark Lantz
IEEE International Congress on Big Data (BigData Congress), 2018

In storage systems, the relevance of files to users can be taken into account to determine storage control policies to reduce cost, while retaining high reliability and performance. The relevance of a file can be estimated by applying supervised learning and using the metadata as features. However, supervised learning requires many training samples to achieve an acceptable estimation accuracy. In this paper, we propose a novel graph-based learning system for the relevance estimation of files using a small training set. First, files are grouped into different file-sets based on the available metadata. Then a parameterized similarity metric among files is introduced for each file-set using the knowledge of the metadata. Finally, message passing over a bipartite graph is applied for relevance estimation. The proposed system is tested on various datasets and compared with logistic regression.

BibTeX, IEEE

Thumbnail of Discovering similarities for content-based recommendation and browsing in multimedia collections

Discovering similarities for content-based recommendation and browsing in multimedia collections

Taras Lehinevych, Nikolaos Kokkinis-Ntrenis, Giorgos Siantikos, A Seza Dogruoz, Theodoros Giannakopoulos, and Stasinos Konstantopoulos
Tenth International Conference on Signal-Image Technology and Internet-Based Systems, 2014

The purpose of the research described in this paper is to examine the existence of correlation between low level audio, visual and textual features and movie content similarity. In order to focus on a well defined and controlled case, we have built a small dataset of movie scenes from three sequel movies. In addition, manual annotations have led to a ground-truth similarity matrix between the adopted scenes. Then, three similarity matrices (one for each medium) have been computed based on Gaussian Mixture Models (audio and visual) and Latent Semantic Indexing (text). We have evaluated the automatically extracted similarities along with two simple fusion approaches and results indicate that the low-level features can lead to an accurate representation of the movie content.

BibTeX, IEEE, Paper (PDF, 673 KB)

Courses & Talks

11/28/19

Course: Introduction to Machine Learning
National University of Kyiv Mohyla Academy

11/24/17

Talk: A Neural Conversational Model
Rails Reactor, Kyiv, Ukraine

Slides, Facebook (ukrainian)

04/23/16

Talk: Apache Spark: Scala vs Python
PyCon Ukraine 2016, Lviv, Ukraine

Slides, Youtube (ukrainian)

07/17/19

What we do in the Shadows GANs
Rails Reactor, Kyiv, Ukraine

Slides, YouTube (ukrainian)

09/07/19

Shadows Generation in the Wild
Data Science fwdays'19, Kyiv, Ukraine

Slides, YouTube (ukrainian)

Contact