• A
  • A
  • A
  • АБВ
  • АБВ
  • АБВ
  • A
  • A
  • A
  • A
  • A
Обычная версия сайта
  • RU
  • EN
  • HSE University
  • Publications
  • Book chapter
  • Equivariant Neural Networks with Geometric Algebras: A New Approach
  • RU
  • EN
Расширенный поиск
Высшая школа экономики
Национальный исследовательский университет
Priority areas
  • business informatics
  • economics
  • engineering science
  • humanitarian
  • IT and mathematics
  • law
  • management
  • mathematics
  • sociology
  • state and public administration
by year
  • 2027
  • 2026
  • 2025
  • 2024
  • 2023
  • 2022
  • 2021
  • 2020
  • 2019
  • 2018
  • 2017
  • 2016
  • 2015
  • 2014
  • 2013
  • 2012
  • 2011
  • 2010
  • 2009
  • 2008
  • 2007
  • 2006
  • 2005
  • 2004
  • 2003
  • 2002
  • 2001
  • 2000
  • 1999
  • 1998
  • 1997
  • 1996
  • 1995
  • 1994
  • 1993
  • 1992
  • 1991
  • 1990
  • 1989
  • 1988
  • 1987
  • 1986
  • 1985
  • 1984
  • 1983
  • 1982
  • 1981
  • 1980
  • 1979
  • 1978
  • 1977
  • 1976
  • 1975
  • 1974
  • 1973
  • 1972
  • 1971
  • 1970
  • 1969
  • 1968
  • 1967
  • 1966
  • 1965
  • 1964
  • 1963
  • 1958
  • More
Subject
News
May 25, 2026
HSE Scientists Train Neural Network to 'Hear' Faults in Electric Motors
Researchers at the AI and Digital Science Institute of the HSE Faculty of Computer Science have developed a new method—the Signature-Guided Data Augmentation (SGDA) framework—that achieves 99% accuracy in motor fault detection and 86% accuracy in fault classification. The application of this approach can reduce industrial equipment repair costs, minimise downtime, and improve production safety. The study results have been published in Engineering Applications of Artificial Intelligence.
May 25, 2026
'The Humanities Serve as a Conscience'
Maria Mizernaia studies Soviet literature and the history of book publishing. In this interview for the HSE Young Scientists project, she discusses plans to publish a novel about besieged Leningrad, AI-provoked reflections on what it means to be human, and how novels can help satisfy our dopamine hunger.
May 25, 2026
Is It Possible to Predict a Citys Life Based on the Shape of Its Neighbourhoods?
Is it possible to predict, based on the configuration of streets and buildings, where a café will open or where traffic congestion will occur? Participants in the Spatial Analysis and Modelling of Urban Processes research and study group use open data and machine learning to identify universal patterns. Alexander Sheludkov and Eduard Somov discuss the purpose of comparing cities, the need for new forms of urban statistics, and how open data is transforming approaches to urban studies.

 

Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!

Publications
  • Books
  • Articles
  • Chapters of books
  • Working papers
  • Report a publication
  • Research at HSE

?

Equivariant Neural Networks with Geometric Algebras: A New Approach

P. 1–8.
Filimoshina E., Shirokov D.

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 generalized Lipschitz groups and prove for the first time that the following mappings in geometric algebras are equivariant with respect to these groups and pseudo-orthogonal and complex orthogonal groups: projections onto subspaces determined by grade involution and reversion and polynomials of geometric algebra elements. Leveraging these equivariant mappings, we design generalized geometric product and linear layers. GLGENN demonstrate superior performance in benchmark equivariant regression tasks, outperforming competitors, while using fewer optimizable parameters. Due to a relatively small number of parameters in the architecture, GLGENN have less tendency to overfitting. GLGENN have promising applications in natural science and computer vision, where tasks inherently involve equivariance to pseudo-orthogonal transformations. Code is available at https://github.com/katyafilimoshina/glgenn-core.

Language: English
Full text
DOI
Text on another site
Keywords: Clifford algebrageometric algebraGeometric deep learningPseudo-orthogonal groupLipschitz groupspin groupequivariant neural network

In book

2025 International Joint Conference on Neural Networks (IJCNN)
IEEE, 2025.
Similar publications
On Lie Groups Preserving Subspaces of Degenerate Clifford Algebras
Filimoshina E., Shirokov D., Advances in Applied Clifford Algebras 2026 Vol. 36 Article 16
This paper introduces Lie groups in degenerate geometric (Clifford) algebras that preserve four fundamental subspaces determined by the grade involution and reversion under the adjoint and twisted adjoint representations. We prove that these Lie groups can be equivalently defined using norm functions of multivectors applied in the theory of spin groups. We also study the ...
Added: January 12, 2026
Prediction of protein-protein interactions using point transformer and spherical Convex Hull graphs
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
Lorentz Invariance of the Multidimensional Dirac–Hestenes Equation
Sofia Rumyantseva, Shirokov D., Advances in Applied Clifford Algebras 2026 Vol. 36 Article 5
This paper investigates the Lorentz invariance of the multidimensional Dirac–Hestenes equation, that is, whether the equation remains form-invariant under pseudo-orthogonal transformations of the coordinates. We examine two distinct approaches: the tensor formulation and the spinor formulation. We first present a detailed examination of the four-dimensional Dirac–Hestenes equation, comparing both transformation approaches. These results are subsequently ...
Added: December 19, 2025
On Commutative Analogues of Clifford Algebras and Their Decompositions
Sharma H., Shirokov D., Advances in Applied Clifford Algebras 2026 Vol. 36 Article 9
We investigate commutative analogues of Clifford algebras - algebras whose generators square to ±1 but commute, instead of anti-commuting as they do in Clifford algebras. We observe that commutativity allows for elegant results. We note that these algebras generalise multicomplex spaces - we show that a commutative analogue of Clifford algebra is either isomorphic to a multicomplex space ...
Added: December 2, 2025
GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras
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
Determinant, Characteristic Polynomial, and Inverse in Commutative Analogues of Clifford Algebras
Sharma H., Shirokov D., Advances in Applied Clifford Algebras 2025 Vol. 35 Article 44
Commutative analogues of Clifford algebras are algebras defined in the same way as Clifford algebras except that their generators commute with each other, in contrast to Clifford algebras in which the generators anticommute. In this paper, we solve the problem of finding multiplicative inverses in commutative analogues of Clifford algebras by introducing a matrix representation ...
Added: October 2, 2025
On Grade Automorphism in Ternary Clifford Algebras
Shirokov D., , in: Hypercomplex Analysis and Its Applications.Extended Abstracts of the International Conference Celebrating Paula Cerejeiras’ 60th Birthday. ICHAA 2024. Trends in Mathematics (TM, volume 9)Vol. 9.: Birkhäuser, 2025. P. 143–150.
For the first time, we introduce a grade automorphism in ternary Clifford algebras and discuss a number of its properties. This operation is not an involution, but naturally generalizes the grade involution (or the main involution) in ordinary (quadratic) Clifford algebras. The new operation can be used in different applications of ternary Clifford algebras in ...
Added: July 6, 2025
Generalized Degenerate Clifford and Lipschitz Groups in Geometric Algebras
Filimoshina E., Shirokov D., Advances in Applied Clifford Algebras 2025 Vol. 35 Article 29
This paper introduces and studies generalized degenerate Clifford and Lipschitz groups in geometric (Clifford) algebras. These Lie groups preserve the direct sums of the subspaces determined by the grade involution and reversion under the adjoint and twisted adjoint representations in degenerate geometric algebras. We prove that the generalized degenerate Clifford and Lipschitz groups can be ...
Added: May 29, 2025
On SU(3) in Ternary Clifford Algebra
Shirokov D., , in: Advances in Computer Graphics: 41st Computer Graphics International Conference, CGI 2024, Geneva, Switzerland, July 1–5, 2024, Proceedings, Part IIIVol. 15340.: Springer, 2025. P. 336–348.
Added: April 1, 2025
Generalized Degenerate Clifford and Lipschitz Groups
Filimoshina E., Dmitry Shirokov, , in: Advances in Computer Graphics: 41st Computer Graphics International Conference, CGI 2024, Geneva, Switzerland, July 1–5, 2024, Proceedings, Part IIIVol. 15340.: Springer, 2025. P. 364–376.
This paper introduces generalized Clifford and Lipschitz groups in degenerate geometric (Clifford) algebras. These groups preserve the direct sums of the subspaces determined by the grade involution and the reversion under the adjoint and twisted adjoint representations. We prove that the generalized degenerate Clifford and Lipschitz groups can be defined using centralizers and twisted centralizers ...
Added: April 1, 2025
  • About
  • About
  • Key Figures & Facts
  • Sustainability at HSE University
  • Faculties & Departments
  • International Partnerships
  • Faculty & Staff
  • HSE Buildings
  • HSE University for Persons with Disabilities
  • Public Enquiries
  • Studies
  • Admissions
  • Programme Catalogue
  • Undergraduate
  • Graduate
  • Exchange Programmes
  • Summer University
  • Summer Schools
  • Semester in Moscow
  • Business Internship
  • Research
  • International Laboratories
  • Research Centres
  • Research Projects
  • Monitoring Studies
  • Conferences & Seminars
  • Academic Jobs
  • Yasin (April) International Academic Conference on Economic and Social Development
  • Media & Resources
  • Publications by staff
  • HSE Journals
  • Publishing House
  • iq.hse.ru: commentary by HSE experts
  • Library
  • Economic & Social Data Archive
  • Video
  • HSE Repository of Socio-Economic Information
  • HSE1993–2026
  • Contacts
  • Copyright
  • Privacy Policy
  • Site Map
Edit