Hodge-Aware Contrastive Learning

Simplicial complexes prove effective in modeling data with multiway dependencies, such as data defined along the edges of networks or within other higher-order structures. Their spectrum can be decomposed into three interpretable subspaces via the Hodge decomposition, resulting foundational in numer...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-09
Hauptverfasser:	Möllers, Alexander, Immer, Alexander, tuin, Vincent, Isufi, Elvin
Format:	Artikel
Sprache:	eng
Schlagworte:	Decomposition Machine learning Neural networks Self-supervised learning Subspaces
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!