Journal article icon

Journal article

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 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.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Publisher copy:
10.1038/s41467-025-61475-w

Authors


More by this author
Role:
Author
ORCID:
0000-0002-3366-4706
More by this author
Institution:
University of Oxford
Research group:
Centre for Eudaimonia and Human Flourishing
Role:
Author
ORCID:
0000-0001-7790-6183
More by this author
Role:
Author
ORCID:
0000-0001-7794-3064


Publisher:
Springer Nature
Journal:
Nature Communications More from this journal
Volume:
16
Issue:
1
Article number:
6511
Publication date:
2025-07-24
Acceptance date:
2025-06-23
DOI:
EISSN:
2041-1723
ISSN:
2041-1723


Language:
English
Pubs id:
2268936
Local pid:
pubs:2268936
Source identifiers:
3144428
Deposit date:
2025-07-24

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP