Explosive neural networks via higher-order interactions in curved statistical manifolds

Abstract Higher-order interactions underlie complex phenomena in systems such as biological and artificial neural networks, but their study is challenging due to the scarcity of tractable models. By leveraging a generalisation of the maximum entropy principle, we introduce curved neural networks as...

Full description

Saved in:
Bibliographic Details
Main Authors: Miguel Aguilera, Pablo A. Morales, Fernando E. Rosas, Hideaki Shimazaki
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-61475-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849342729812705280
author Miguel Aguilera
Pablo A. Morales
Fernando E. Rosas
Hideaki Shimazaki
author_facet Miguel Aguilera
Pablo A. Morales
Fernando E. Rosas
Hideaki Shimazaki
author_sort Miguel Aguilera
collection DOAJ
description Abstract Higher-order interactions underlie complex phenomena in systems such as biological and artificial neural networks, but their study is challenging due to the scarcity of tractable models. By leveraging a generalisation of the maximum entropy principle, we introduce curved neural networks as a class of models with a limited number of parameters that are particularly well-suited for studying higher-order phenomena. Through exact mean-field descriptions, we show that these curved neural networks implement a self-regulating annealing process that can accelerate memory retrieval, leading to explosive order-disorder phase transitions with multi-stability and hysteresis effects. Moreover, by analytically exploring their memory-retrieval capacity using the replica trick, we demonstrate that these networks can enhance memory capacity and robustness of retrieval over classical associative-memory networks. Overall, the proposed framework provides parsimonious models amenable to analytical study, revealing higher-order phenomena in complex networks.
format Article
id doaj-art-ff94f5df904246db8ba284ee53a9adf2
institution Kabale University
issn 2041-1723
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-ff94f5df904246db8ba284ee53a9adf22025-08-20T03:43:16ZengNature PortfolioNature Communications2041-17232025-07-0116111010.1038/s41467-025-61475-wExplosive neural networks via higher-order interactions in curved statistical manifoldsMiguel Aguilera0Pablo A. Morales1Fernando E. Rosas2Hideaki Shimazaki3BCAM – Basque Center for Applied MathematicsResearch Division, Araya Inc.Sussex AI and Sussex Centre for Consciousness Science, Department of Informatics, University of SussexGraduate School of Informatics, Kyoto UniversityAbstract Higher-order interactions underlie complex phenomena in systems such as biological and artificial neural networks, but their study is challenging due to the scarcity of tractable models. By leveraging a generalisation of the maximum entropy principle, we introduce curved neural networks as a class of models with a limited number of parameters that are particularly well-suited for studying higher-order phenomena. Through exact mean-field descriptions, we show that these curved neural networks implement a self-regulating annealing process that can accelerate memory retrieval, leading to explosive order-disorder phase transitions with multi-stability and hysteresis effects. Moreover, by analytically exploring their memory-retrieval capacity using the replica trick, we demonstrate that these networks can enhance memory capacity and robustness of retrieval over classical associative-memory networks. Overall, the proposed framework provides parsimonious models amenable to analytical study, revealing higher-order phenomena in complex networks.https://doi.org/10.1038/s41467-025-61475-w
spellingShingle Miguel Aguilera
Pablo A. Morales
Fernando E. Rosas
Hideaki Shimazaki
Explosive neural networks via higher-order interactions in curved statistical manifolds
Nature Communications
title Explosive neural networks via higher-order interactions in curved statistical manifolds
title_full Explosive neural networks via higher-order interactions in curved statistical manifolds
title_fullStr Explosive neural networks via higher-order interactions in curved statistical manifolds
title_full_unstemmed Explosive neural networks via higher-order interactions in curved statistical manifolds
title_short Explosive neural networks via higher-order interactions in curved statistical manifolds
title_sort explosive neural networks via higher order interactions in curved statistical manifolds
url https://doi.org/10.1038/s41467-025-61475-w
work_keys_str_mv AT miguelaguilera explosiveneuralnetworksviahigherorderinteractionsincurvedstatisticalmanifolds
AT pabloamorales explosiveneuralnetworksviahigherorderinteractionsincurvedstatisticalmanifolds
AT fernandoerosas explosiveneuralnetworksviahigherorderinteractionsincurvedstatisticalmanifolds
AT hideakishimazaki explosiveneuralnetworksviahigherorderinteractionsincurvedstatisticalmanifolds