SGRiT: Non-Negative Matrix Factorization via Subspace Graph Regularization and Riemannian-Based Trust Region Algorithm

Non-negative Matrix Factorization (NMF) has gained popularity due to its effectiveness in clustering and feature selection tasks. It is particularly valuable for managing high-dimensional data by reducing dimensionality and providing meaningful semantic representations. However, traditional NMF meth...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Machine learning and knowledge extraction Jg. 7; H. 1; S. 25
Hauptverfasser:	Nokhodchian, Mohsen, Moattar, Mohammad Hossein, Jalali, Mehrdad
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 01.03.2025
Schlagworte:	Algorithms Analysis Clustering Comparative analysis Data compression Datasets Decomposition dimension reduction Euclidean space Factorization Geometry Machine learning Manifolds (mathematics) Mathematical optimization Matrix decomposition Methods Non-negative Matrix Factorization Optimization Optimization techniques Outliers (statistics) Regularization Representations Riemannian manifolds Sparsity Stiefel manifold subspace graph regularization Subspaces Germany Iran
ISSN:	2504-4990, 2504-4990
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!