Knowledge Graph Completion with Mixed Geometry Tensor Factorization

This paper studies tensors that admit decomposition in the Extended Tensor Train (ETT) format, with a key focus on the case where some decomposition factors are constrained to be equal. This factor sharing introduces additional challenges, as it breaks the multilinear structure of the decomposition. Nevertheless, we show that Riemannian optimization methods can naturally handle ...

Added: December 22, 2025

Leveraging Geometric Insights in Hyperbolic Triplet Loss for Improved Recommendations

Yusupov V., Rakhuba M., Frolov E., , in: RecSys '25: Proceedings of the Nineteenth ACM Conference on Recommender Systems.: ACM, 2025. Ch. 1 P. 1217–1221.

Recent studies have demonstrated the potential of hyperbolic geometry for capturing complex patterns from interaction data in recommender systems. In this work, we introduce a novel hyperbolic recommendation model that uses geometrical insights to improve representation learning and increase computational stability at the same time. We reformulate the notion of hyperbolic distances to unlock additional ...

Added: October 3, 2025

Self-Attentive Sequential Recommendations with Hyperbolic Representations

Evgeny Frolov, Tatyana Matveeva, Mirvakhabova L. et al., , in: RecSys '24: Proceedings of the 18th ACM Conference on Recommender Systems.: Association for Computing Machinery (ACM), 2024. P. 981–986.

Added: September 10, 2024

Synthesis of multilevel knowledge graphs: Methods and technologies for dynamic networks

Man T., Vodyaho A., Ignatov D. I. et al., Engineering Applications of Artificial Intelligence 2023 Vol. 123 Article 106244

Knowledge Graphs is one of the most popular techniques for knowledge-based modelling in various subdomains of modern AI technologies ranging from natural language processing to e-commerce recommendations and cyberphysical systems. Even complex technical systems like telecommunication networks could be modelled by means of Knowledge Graphs. However, there are serious challenges when we deal with such ...

Added: November 23, 2023

Tensor methods and recommender systems

Frolov E., Oseledets I., Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 2017 Vol. 7 No. 3

Added: November 16, 2023

Tensor-Based Sequential Learning via Hankel Matrix Representation for Next Item Recommendations

Frolov E., Oseledets I., IEEE Access 2023 Vol. 11 P. 6357–6371

Self-attentive transformer models have recently been shown to solve the next item recommendation task very efficiently. The learned attention weights capture sequential dynamics in user behavior and generalize well. Motivated by the special structure of learned parameter space, we question if it is possible to mimic it with an alternative and more lightweight approach. We ...

Added: November 16, 2023

Towards Practical Control of Singular Values of Convolutional Layers

Senderovich A., Bulatova E., Obukhov A. et al., , in: Thirty-Sixth Conference on Neural Information Processing Systems : NeurIPS 2022.: Curran Associates, Inc., 2022. P. 10918–10930.

Added: January 24, 2023

Analyzing COVID-19 Medical Papers Using Artificial Intelligence: Insights for Researchers and Medical Professionals

Dmitry Soshnikov, Petrova T., Soshnikova V. et al., Big Data and Cognitive Computing 2022 Vol. 6 No. 1 Article 4

Since the beginning of the COVID-19 pandemic almost two years ago, there have been more than 700,000 scientific papers published on the subject. An individual researcher cannot possibly get acquainted with such a huge text corpus and, therefore, some help from artificial intelligence (AI) is highly needed. We propose the AI-based tool to help researchers ...

Added: February 22, 2022

MARS: Masked Automatic Ranks Selection in Tensor Decompositions

Kodryan M., Kropotov D., Vetrov D., / Series QTNML 2020 "First Workshop on Quantum Tensor Networks in Machine Learning, NeurIPS 2020". 2020.

Tensor decomposition methods have recently proven to be efficient for compressing and accelerating neural networks. However, the problem of optimal decomposition structure determination is still not well studied while being quite important. Specifically, decomposition ranks present the crucial parameter controlling the compression-accuracy trade-off. In this paper, we introduce MARS - a new efficient method for ...

Added: February 5, 2021

Cross-Domain Co-Author Recommendation Based on Knowledge Graph Clustering

Ahmed Munna M. T., Delhibabu R., , in: Intelligent Information and Database Systems: 13th Asian Conference, ACIIDS 2021, Phuket, Thailand, April 7–10, 2021, Proceedings.: Springer, 2021. P. 782–795.

Nowadays, due to the growing demand for interdisciplinary research and innovation, different scientific communities pay substantial attention to cross-domain collaboration. However, having only information retrieval technologies in hands might be not enough to find prospective collaborators due to the large volume of stored bibliographic records in scholarly databases and unawareness about emerging cross-disciplinary trends. To ...

Added: January 14, 2021

Tensor Rank bounds for Point Singularities in ℝ^3

Marcati C., Rakhuba M., Christoph S., / Series math "arxiv.org". 2020.

We analyze rates of approximation by quantized, tensor-structured representations of functions with isolated point singularities in ℝ3. We consider functions in countably normed Sobolev spaces with radial weights and analytic- or Gevrey-type control of weighted semi-norms. Several classes of boundary value and eigenvalue problems from science and engineering are discussed whose solutions belong to the countably ...

Added: October 20, 2020

Quantized tensor FEM for multiscale problems: diffusion problems in two and three dimensions

Kazeev V., Oseledets I., Rakhuba M. et al., / Series math "arxiv.org". 2020.

Homogenization in terms of multiscale limits transforms a multiscale problem with n+1 asymptotically separated microscales posed on a physical domain D⊂ℝd into a one-scale problem posed on a product domain of dimension (n+1)d by introducing n so-called "fast variables". This procedure allows to convert n+1 scales in d physical dimensions into a single-scale structure in (n+1)d dimensions. We prove here that both the original, physical multiscale problem and the ...

Added: October 20, 2020