Feature-enriched hyperbolic network geometry

Graph-structured data provide an integrated description of complex systems, encompassing not only the interactions among nodes, but also the intrinsic features that characterize these nodes. These features play a fundamental role in the formation of links within the network, making them valuable for...

Full description

Saved in:
Bibliographic Details
Main Authors: Roya Aliakbarisani, M. Ángeles Serrano, Marián Boguñá
Format: Article
Language:English
Published: American Physical Society 2025-07-01
Series:Physical Review Research
Online Access:http://doi.org/10.1103/PhysRevResearch.7.033036
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850094959680552960
author Roya Aliakbarisani
M. Ángeles Serrano
Marián Boguñá
author_facet Roya Aliakbarisani
M. Ángeles Serrano
Marián Boguñá
author_sort Roya Aliakbarisani
collection DOAJ
description Graph-structured data provide an integrated description of complex systems, encompassing not only the interactions among nodes, but also the intrinsic features that characterize these nodes. These features play a fundamental role in the formation of links within the network, making them valuable for extracting meaningful information. In this paper, we present a comprehensive framework that treats features as tangible entities and establishes a bipartite graph connecting nodes and features. By assuming that nodes sharing similarities should also share features, we introduce a hyperbolic geometric space where both nodes and features coexist, shaping the structure of both the node network and the bipartite network of nodes and features. Through this framework, we can identify correlations between nodes and features in real data and generate synthetic datasets that mimic the topological properties of their connectivity patterns. Notably, node features are at the core of deep learning techniques, such as graph convolutional neural networks (GCNs), offering great utility in downstream tasks. Therefore, our approach provides insights into the inner workings of GCNs by revealing the intricate structure of the data.
format Article
id doaj-art-9e46584e774a4b19ae008f16a2b56302
institution DOAJ
issn 2643-1564
language English
publishDate 2025-07-01
publisher American Physical Society
record_format Article
series Physical Review Research
spelling doaj-art-9e46584e774a4b19ae008f16a2b563022025-08-20T02:41:33ZengAmerican Physical SocietyPhysical Review Research2643-15642025-07-017303303610.1103/PhysRevResearch.7.033036Feature-enriched hyperbolic network geometryRoya AliakbarisaniM. Ángeles SerranoMarián BoguñáGraph-structured data provide an integrated description of complex systems, encompassing not only the interactions among nodes, but also the intrinsic features that characterize these nodes. These features play a fundamental role in the formation of links within the network, making them valuable for extracting meaningful information. In this paper, we present a comprehensive framework that treats features as tangible entities and establishes a bipartite graph connecting nodes and features. By assuming that nodes sharing similarities should also share features, we introduce a hyperbolic geometric space where both nodes and features coexist, shaping the structure of both the node network and the bipartite network of nodes and features. Through this framework, we can identify correlations between nodes and features in real data and generate synthetic datasets that mimic the topological properties of their connectivity patterns. Notably, node features are at the core of deep learning techniques, such as graph convolutional neural networks (GCNs), offering great utility in downstream tasks. Therefore, our approach provides insights into the inner workings of GCNs by revealing the intricate structure of the data.http://doi.org/10.1103/PhysRevResearch.7.033036
spellingShingle Roya Aliakbarisani
M. Ángeles Serrano
Marián Boguñá
Feature-enriched hyperbolic network geometry
Physical Review Research
title Feature-enriched hyperbolic network geometry
title_full Feature-enriched hyperbolic network geometry
title_fullStr Feature-enriched hyperbolic network geometry
title_full_unstemmed Feature-enriched hyperbolic network geometry
title_short Feature-enriched hyperbolic network geometry
title_sort feature enriched hyperbolic network geometry
url http://doi.org/10.1103/PhysRevResearch.7.033036
work_keys_str_mv AT royaaliakbarisani featureenrichedhyperbolicnetworkgeometry
AT mangelesserrano featureenrichedhyperbolicnetworkgeometry
AT marianboguna featureenrichedhyperbolicnetworkgeometry