A factor graph model for unsupervised feature selection

•A novel filter type unsupervised feature selection algorithm, namely, a factor graph model for unsupervised feature selection (FGUFS) is proposed.•In FGUFS, the maximal information coefficient (MIC) is used to measure the similarities between features, and a message passing algorithm developed for...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Information sciences Jg. 480; S. 144 - 159
Hauptverfasser: Wang, Hongjun, Zhang, Yinghui, Zhang, Ji, Li, Tianrui, Peng, Lingxi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.04.2019
Schlagworte:
Factor graph
Feature selection
Message-passing algorithm
Unsupervised learning
Feature selection
Factor graph
Message-passing algorithm
Unsupervised learning
ISSN:0020-0255, 1872-6291
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•A novel filter type unsupervised feature selection algorithm, namely, a factor graph model for unsupervised feature selection (FGUFS) is proposed.•In FGUFS, the maximal information coefficient (MIC) is used to measure the similarities between features, and a message passing algorithm developed for the purpose is used to infer the factor graph.•Extensive experiments show the strengths of FGUFS over existing methods to achieve high clustering accuracy, RI and purity while containing few redundant features. In this paper, a factor graph model for unsupervised feature selection (FGUFS) is proposed. FGUFS explicitly measures the similarities between features; these similarities are passed to each other as messages in the graph model. The importance score of each feature is calculated using the message-passing algorithm, and then feature selection is performed based on the final importance scores. Extensive experiments were performed on several datasets, and the results demonstrate that FGUFS outperforms other state-of-art unsupervised feature selection algorithms on several performance measures.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2018.12.034