?
Network Embedding for Cluster Analysis
P. 000127–000130.
Makarov I., Oborevich A.
Graph visualization is an effective and efficient way to discover complex inter-connections between elements within the nested structure of data. To accomplish this type of representation machine learning algorithms use a technique called graph embedding and node embedding in particular. However, in this paper, we will compare well-known techniques to yet largely under-explored setting of graph embedding named community embedding: embedding individual communities instead of individual nodes. This type of embedding can be especially useful in graph visualization and community detection tasks. Despite the fact that graph embedding and clustering tasks are separate, a good solution to the first one tends to have a correlation with the solution of the second problem and may have a positive impact if knowledge is transferred.
David Arteaga, Poptsova M., Computational and Structural Biotechnology Journal 2026 Vol. 31 P. 82–93
Accurate predictions and large-scale identification of protein-protein interactions (PPIs) are crucial for understanding their inherent biological mechanisms and protein functions in virtually all biological processes. Nowadays, graph-based deep learning models have made significant contributions in modeling proteins with physicochemical and geometric features. However, most of these models rely on conventional graph construction methods, such as ...
Added: December 22, 2025
Filimoshina E., Shirokov D., , in: 2025 International Joint Conference on Neural Networks (IJCNN).: IEEE, 2025. P. 1–8.
This work is devoted to construction and implementation of new equivariant neural networks based on geometric (Clifford) algebras. We propose, implement, test, and compare with competitors a new architecture of equivariant neural networks, which we call Generalized Lipschitz Group Equivariant Neural Networks (GLGENN). These networks are equivariant to all pseudo-orthogonal transformations, including rotations. We introduce ...
Added: November 15, 2025
Filimoshina E., Shirokov D., , in: Volume 267: International Conference on Machine Learning, 13-19 July 2025, Vancouver Convention Center, Vancouver, CanadaVol. 267.: [б.и.], 2025. P. 17153–17188.
We propose, implement, and compare with competitors a new architecture of equivariant neural networks based on geometric (Clifford) algebras: Generalized Lipschitz Group Equivariant Neural Networks (GLGENN). These networks are equivariant to all pseudo-orthogonal transformations, including rotations and reflections, of a vector space with any non-degenerate or degenerate symmetric bilinear form. We propose a weight-sharing parametrization ...
Added: October 28, 2025
Shalileh S., Social Network Analysis and Mining 2025 Vol. 15212 P. 137–148
Community detection in attributed networks aims to recover clusters in which the within-community nodes are as interconnected and as homogeneous as possible, while the between-communities nodes are as disconnected and as heterogeneous as possible. The current research proposes a straightforward data-driven model with an integrated regularization term to recover communities. For further improvement of the ...
Added: November 30, 2024
Popov V., Chepovskiy A., , in: Complex Networks & Their Applications XIII, Proceedings of The Thirteenth International Conference on Complex Networks and Their Applications: COMPLEX NETWORKS 2024 - Volume 3.: Springer, 2025. P. 83–90.
Added: September 20, 2024
Noskov F., Panov M., / Series arXiv "math". 2023.
Community detection is one of the most critical problems in modern network science. Its applications can be found in various fields, from protein modeling to social network analysis. Recently, many papers appeared studying the problem of overlapping community detection, where each node of a network may belong to several communities. In this work, we consider ...
Added: May 31, 2024
Shalileh S., Mirkin B., , in: Complex Networks & Their Applications XII: Proceedings of The Twelfth International Conference on Complex Networks and their Applications: COMPLEX NETWORKS 2023, Volume 2.: Springer, 2024. Ch. 15 P. 185–196.
Added: March 5, 2024
Alina V. Vladimirova, , in: Alternative Paths to Influence: Soft Power and International Politics.: Oxon: Routledge, 2023. Ch. 9 P. 556–571.
Soft power is one of the most influential concepts in the discipline of international relations, yet it is highly criticized for ambiguity and analytical weakness. Thus, through thoughtful literature reviews, scholars continue with clarifying and mapping the theory within a broader political power research programme. It is in this scholarly context that this article offers ...
Added: February 14, 2024
Alina V. Vladimirova, Journal of political power 2022 Vol. 15 No. 3 P. 556–571
Soft power is one of the most influential concepts in the discipline of international relations, yet it is highly criticized for ambiguity and analytical weakness. Thus, through thoughtful literature reviews, scholars continue with clarifying and mapping the theory within a broader political power research programme. It is in this scholarly context that this article offers ...
Added: February 14, 2024
Chepovskiy A., , in: The 6th International Conference on Complex Networks and Their Applications. Nov. 29 - Dec. 01, 2017, Lyon (France), Book of abstracts. ISBN 978-2-9557050-2-5.: Springer, 2017. P. 336–340.
One of the tasks related to the study of the of complex networks is the problem of revealing communities structure. Algorithms to split all vertices into groups, named communities, so that the vertices of each group are more closely related to each other than to the rest of the graph are widely investigated nowadays. This is so-called ...
Added: March 22, 2023
Chepovskiy A., Вопросы кибербезопасности 2023 № 1(53) С. 75–81
The purpose of the study: search for a technique for constructing and analyzing a graph of interacting objects in the network of Telegram channels, including the calculation of psycholinguistic characteristics of texts. This technique makes it possible to classify groups of channels and evaluate their informational impact on users.
Method: (U, M, R)-model is used to build a weighted ...
Added: March 6, 2023
Anton I.N. Begehr, Peter B. Panfilov, , in: 2022 IEEE 24th Conference on Business Informatics (CBI)Vol. 2: CBI Forum and Workshop Papers.: IEEE, 2022. P. 88–96.
Graphs, such as social networks, emerge naturally from various real-world situations. Recently, graph embedding methods have gained traction in data science research. The graph and community embedding algorithm ComE aims to preserve first-, second- and higher-order proximity. ComE requires prior knowledge of the number of communities K. In this paper, ComE is extended to utilize ...
Added: December 6, 2022
Chepovskiy A., М.: Национальный открытый университет «ИНТУИТ», 2022.
В монографии рассмотрены различные математические модели для решения задач анализа сетей взаимодействующих объектов систем телекоммуникаций. Предназначена для разработчиков информационных систем, специалистов в области анализа данных. ...
Added: November 18, 2022
Giordano M., Maddalena L., Manzo M. et al., Annals of Mathematics and Artificial Intelligence 2023 Vol. 91 P. 259–285
As the number of graph-level embedding techniques increases at an unprecedented speed, questions arise about their behavior and performance when training data undergo perturbations. This is the case when an external entity maliciously alters training data to invalidate the embedding. This paper explores the efects of such attacks on some graph datasets by applying diferent ...
Added: November 18, 2022
Popov V., Chepovskiy A., Труды Института системного анализа Российской академии наук 2022 Т. 72 № 4 С. 39–50
In this paper, the authors present the “Galaxies method” to reveal implicit communities on the
graph of interacting objects obtained by importing a network of channels from the Telegram messenger. This
method is based on successive identification of overlapping communities on the initial weighted graph, further
construction of a new graph, in which the vertices are the communities ...
Added: October 30, 2022
Popov V., Chepovskiy A., Вестник Новосибирского государственного университета. Серия: Информационные технологии 2022 Т. 20 № 2 С. 60–71
In this paper, an algorithm to import data from the messenger Telegram and to build weighted graphs of interacting objects is described. To import data, the given Telegram-channels are taken as a basis. Then, iteractively channels that had any of the recorded three interactions with previous ones are revealed: common external links, mentions of each ...
Added: September 2, 2022
Gerasimova O., Makarov I., Лапидус А. А., , in: Analysis of Images, Social Networks and Texts. 10th International Conference, AIST 2021, Tbilisi, Georgia, December 16–18, 2021, Revised Selected Papers.: Cham: Springer, 2022. P. 1–14.
The work is devoted to academic papers recommendation task considered as link prediction on a static citation network. We compare several graph embeddings, text-based and fusion models in the link prediction problem on academic papers citation dataset. We showed that fusion models of graph and text information outperform other approaches based on graph or text information alone. We prove ...
Added: December 3, 2021
Popov V., Chepovskiy A., Вестник Новосибирского государственного университета. Серия: Информационные технологии 2021 Т. 19 № 2 С. 76–91
In this paper, the authors describe an algorithm for importing data from the social network Twitter and building weighted social graphs. To import data, the given posts are taken as a basis, users who have had any of the recorded interactions with them are downloaded. Further, the algorithm focuses on the given configuration and uses ...
Added: July 25, 2021
Makarov I., Makarov M., Kiselev D., PeerJ Computer Science 2021 Vol. 7 Article e526
Today, increased attention is drawn towards network representation learning, a technique that maps nodes of a network into vectors of a low-dimensional embedding space. A network embedding constructed this way aims to preserve nodes similarity and other specific network properties. Embedding vectors can later be used for downstream machine learning problems, such as node classification, ...
Added: March 31, 2021
Chepovskiy A., Leshchev D. A., Khaykova S.P., , in: Complex Networks & Their Applications IX. Volume 1: Proceedings of the Ninth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2020.: Springer, 2021. P. 38–50.
The processing of networks of interacting objects makes it possible to solve topical issues in the modern world of identifying opinion leaders and channels for the dissemination and exchange of information. In this work, the structure of networks of interacting objects and their possible analysis with the help of weighted graphs based on the interaction ...
Added: January 6, 2021