?
JONNEE: Joint Network Nodes and Edges Embedding
IEEE Access. 2021. Vol. 9. P. 144646–144659.
Recently, graph embedding models significantly improved the quality of graph machine learning tasks, such as node classification and link prediction. In this work, we propose a model called JONNEE (JOint Network Nodes and Edges Embedding), which learns node and edge embeddings under self-supervision via joint constraints in a given graph and its edge-to-vertex dual representation as a Line graph. The model uses two graph autoencoders with additional structural feature engineering and several regularization techniques to train for an adjacency matrix reconstruction task in an unsupervised setting. Experimental results show that our model performs on par with state-of-the-art undirected attribute graph embedding models and requires less number of epochs to achieve the same quality due to Line graph self-supervision under a unified embedding framework.
Kh. Kh. Abdullin, D. B. Mokeev, D. S. Taletskii, Mathematical notes 2026 Vol. 119 No. 1 P. 3–7
By the Ramsey number R(K1,s,Pt) one means the least positive integer n such that, for every n-vertex graph G, the following condition holds: either G contains a vertex of degree at least s or the complement of G contains a simple t-path. In this paper, we fi nd precise values of R(K1,s,Pt) for certain values ...
Added: June 10, 2026
Sorokin D., Kostin A., Savchenko L. et al., Knowledge-Based Systems 2026 Vol. 348 Article 116258
A convenient approach to optimally solving combinatorial optimization tasks is the Branch-and-Bound method.
Its branching heuristic can be learned to solve a large set of similar tasks. The promising results here are
achieved by the recently appeared on-policy reinforcement learning method based on the tree Markov Decision
Process. To overcome its main disadvantages, namely, very large training time ...
Added: June 10, 2026
Namsaraev Z., Kozlova A., Toshchakov S., Scientific Reports 2026 Vol. 16 No. 17769
Distilled fermented milk beverages are rare in food technology, despite the global prevalence of plant-based spirits. Currently, the production of distilled strong alcoholic beverages from fermented milk using traditional technologies is known only among Mongolic-speaking peoples and their Siberian neighbors. This study provides the first interdisciplinary analysis of darasun, a traditional Buryat spirit made from fermented ...
Added: June 10, 2026
Hushchyn M., Butorova A., Bobakov V. et al., European Physical Journal: Special Topics 2026 P. 1–19
This paper presents a review of artificial intelligence (AI) methods for failure prediction in data center cooling systems, with a focus on the integration of digital twins (DTs), physics-informed learning, and graph-based models. Positioned within complex network science, this review addresses a limitation of conventional graph approaches—their reliance on pairwise connectivity—whereas real-world failures often arise ...
Added: June 10, 2026
Springer, 2026.
The book presents the proceedings of the 13th International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA 2024), held at Intelligent Systems Research Group (ISRG), London Metropolitan University, London, United Kingdom, during June 6–7, 2025. Researchers, scientists, engineers and practitioners exchange new ideas and experiences in the domain of intelligent computing theories with ...
Added: June 8, 2026
Flamarion M. V., Pelinovsky E., Nonlinear Dynamics 2026 Vol. 114 Article 784
In this article, we investigate wave packet and solitary wave dynamics in the Whitham–Ostrovsky (WO) equation. By means of a multiple-scales expansion, we formally derive a nonlinear Schrödinger (NLS) equation governing the envelope evolution.The corresponding modulational stability diagram is then obtained using the Lighthill criterion. We show that sufficiently large values of the low-frequency dispersive term render ...
Added: June 5, 2026
Bazhenov G., Platonov O., Prokhorenkova L., , in: 39th Conference on Neural Information Processing Systems (NeurIPS 2025).: NeurIPS, 2025.
Although data that can be naturally represented as graphs is widespread in real-world applications across diverse industries, popular graph ML benchmarks for node property prediction only cover a surprisingly narrow set of data domains, and graph neural networks (GNNs) are often evaluated on just a few academic citation networks. This issue is particularly pressing in ...
Added: November 6, 2025
Makarov D. M., Kalikin N., Budkov Y. et al., Journal of Chemical Information and Modeling 2025 Vol. 65 No. 8 P. 4043–4056
Accurate solubility prediction in supercritical carbon dioxide (scCO2) is crucial for optimizing experimental
design by eliminating unnecessary and costly trials at an early stage, thereby streamlining the workflow. A comprehensive solubility database containing 31,975 records has been compiled, providing a foundation for developing predictive models applicable to a diverse class of chemical compounds, with a particular ...
Added: April 16, 2025
Dayoub Y., Andrey V. Savchenko, Makarov I., , in: 2024 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct).: IEEE, 2024. P. 584–587.
Depth estimation is essential in Augmented Reality applications, enabling realistic object placement, scene understanding, spatial mapping, interaction, and environment awareness. This paper proposes a method to enhance depth model performance without increasing inference costs by improving the pose network in a selfsupervised learning setup. In particular, we enrich spatial information in the pose network by ...
Added: December 3, 2024
Bazhenov G., Kuznedelev D., Malinin A. et al., , in: Advances in Neural Information Processing Systems 36 (NeurIPS 2023).: Curran Associates, Inc., 2023. P. 75567–75594.
In reliable decision-making systems based on machine learning, models have to be robust to distributional shifts or provide the uncertainty of their predictions. In node-level problems of graph learning, distributional shifts can be especially complex since the samples are interdependent. To evaluate the performance of graph models, it is important to test them on diverse ...
Added: February 7, 2024
Maksim Golyadkin, Vitaliy Pozdnyakov, Leonid Zhukov et al., Artificial Intelligence 2023 Vol. 324 Article 104012
Modern industrial facilities generate large volumes of raw sensor data during the production process. This data is used to monitor and control the processes and can be analyzed to detect and predict process abnormalities. Typically, the data has to be annotated by experts in order to be used in predictive modeling. However, manual annotation of ...
Added: September 20, 2023
Li X., Makarov I., Kiselev D., IEEE Access 2023 Vol. 11 P. 91842–91849
Predicting molecular properties with Graph Neural Networks (GNNs) has recently drawn a lot of attention, with compound toxicity prediction being one of the biggest challenges. In cases where there is insufficient labeled molecule data, an effective approach is to pre-train GNNs on large-scale unlabeled molecular data and then fine-tune them for downstream tasks. Among pre-training ...
Added: August 30, 2023
Lukashina N., Kartysheva E., Spjuth O. et al., Journal of Cheminformatics 2022 Vol. 14 Article 49
Polypharmacy refers to the administration of multiple drugs on a daily basis. It has demonstrated effectiveness in treating many complex diseases , but it has a higher risk of adverse drug reactions. Hence, the prediction of polypharmacy side effects is an essential step in drug testing, especially for new drugs. This paper shows that the ...
Added: October 11, 2022
Kiselev D., Makarov I., IEEE Access 2022 Vol. 10 P. 123614–123621
Temporal graph networks are powerful tools for solving the cold-start problem in sequential recommender systems. However, graph models are susceptible to feedback loops and data distribution shifts. The paper proposes a simple yet efficient graph-based exploration method for the mitigation of the issues above. It adopts the counter-based state exploration from reinforcement learning to the ...
Added: September 5, 2022
Makarov I., Bakhanova M., Nikolenko S. et al., PeerJ Computer Science 2022 Vol. 8 Article e865
Depth estimation has been an essential task for many computer vision applications, especially in autonomous driving, where safety is paramount. Depth can be estimated not only with traditional supervised learning but also via a self-supervised approach that relies on camera motion and does not require ground truth depth maps. Recently, major improvements have been introduced ...
Added: February 1, 2022
Sadrtdinov I., Chirkova N., Lobacheva E., , in: ICML 2021 Workshop, Overparameterization: Pitfalls & Opportunities.: [б.и.], 2021.
Memorization studies of deep neural networks (DNNs) help to understand what patterns and how do DNNs learn, and motivate improvements to DNN training approaches. In this work, we investigate the memorization properties of SimCLR, a widely used contrastive self-supervised learning approach, and compare them to the memorization of supervised learning and random labels training. We ...
Added: January 25, 2022
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
Makarov I., Kiselev D., Nikitinsky N. et al., PeerJ Computer Science 2021 Vol. 7 P. 1–62
Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering in order to incorporate structural information into predictive model. Nowadays, a family of automated graph feature engineering techniques have been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs ...
Added: October 27, 2020
Pavel Zolnikov, Zubov M., Nikitinsky N. et al., , in: Proceedings of the Fifth Workshop on Experimental Economics and Machine Learning at the National Research University Higher School of Economics co-located with the Seventh International Conference on Applied Research in Economics (iCare7).: Aachen: CEUR Workshop Proceedings, 2019. P. 57–67.
Network embedding has become a very promising technique in analysis of complex networks. It is a method to project nodes of a network into a low-dimensional vector space while retaining the structure of the network based on vector similarity. There are many methods of network embedding developed for traditional single layer networks. On the other ...
Added: November 19, 2019
Makarov I., Gerasimova O., , in: Proceedings of the 14th International Workshop on Semantic and Social Media Adaptation and Personalization.: NY: IEEE, 2019. P. 1–6.
In this paper, we study the problem of predicting collaborations in co-authorship network. We formulated our task in terms of link prediction problem on weighted co-authorship network, in which authors play the role of nodes, and weighted edges connecting two authors are formed by storing either a number or quality metric of research papers co-authored ...
Added: July 30, 2019
Gerasimova O., Makarov I., , in: Advances in Computational Intelligence. IWANN 2019.: Berlin: Springer, 2019. P. 667–677.
In this paper, we study the problem of predicting quantity of collaborations in co-authorship network. We formulated our task in terms of link prediction problem on weighted co-authorship network, formed by authors writing papers in co-authorship represented by edges between authors in the network. Our task is formulated as regression for edge weights, for which ...
Added: July 29, 2019