Karine Shakhkyan

Dr. Karine Shakhkyan

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 July 2024
Verified
Conference Paper
Open access
MPMaiia Pinchuk
Maiia Pinchuk
GKGrigorii Kirgizov
Grigorii Kirgizov
LYLyubov Yamshchikova
Lyubov Yamshchikova
NNNikolay Nikitin
Nikolay Nikitin
IDIrina Deeva
Irina Deeva
AKAnna Kalyuzhnaya
Anna Kalyuzhnaya
We introduce GOLEM --- an open-source optimization framework for automated design of graph-based structures in various scientific domains. It solves the problem of finding optimal topology and parameters of graphs using evolutionary algorithms, and does it in a modular domain-agnostic way. The paper describes the framework and its flexible approach to domain adaptation. Experimental studies provide several examples of GOLEM application in different fields: Bayesian networks, drug design, and robotics.

1 August 2024 in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
Verified
Journal Article
Open access
PDF file
IDIrina Deeva
Irina Deeva
KSKarine Shakhkyan
Karine Shakhkyan
Jerzy KamińskiJerzy Kamiński
Jerzy Kamiński
The article presents a new approach to modeling nonlinear dependencies called composite Bayesian networks. The main emphasis is on integrating machine learning models into Bayesian networks while maintaining their fundamental principles. The novelty of the approach is that it allows us to solve the problem of data inconsistency with traditional assumptions about dependencies. The presented method consists in selecting a variety of machine learning models at the stage of training composite Bayesian networks. This allows you to flexibly customize the nature of the dependencies in accordance with the requirements and dictated characteristics of the modeled object. The software implementation is made in the form of a specialized framework that describes all the necessary functionality. The results of experiments to evaluate the effectiveness of modeling dependencies between features are presented. Data for the experiments was taken from the bnlearn repository for benchmarks and from the UCI repository for real data. The performance of composite Bayesian networks was validated by comparing the likelihood and F1 score with classical Bayesian networks trained with the Hill-Climbing algorithm, demonstrating high accuracy in representing multivariate distributions. The improvement in benchmarks is insignificant since they contain linear dependencies that are well modeled by the classical algorithm. An average 30 % improvement in likelihood was obtained on real UCI datasets. The obtained data can be applied in areas that require modeling complex dependencies between features, for example, in machine learning, statistics, data analysis, as well as in specific subject areas.