Several contributions to the recent literature have shown that supervised learning is greatly enhanced when only the most relevant features are selected for building the discrimination rule. Unfortunately, outliers and wrongly labelled units may undermine the determination of relevant predictors, and almost no dedicated methodologies have been developed to face this issue. In the present paper, we introduce a new robust variable selection approach, that embeds a classifier within a greedy-forward procedure. An experiment on synthetic data is provided, to under- line the benefits of the proposed method in comparison with non-robust solutions.

Cappozzo, A., Greselin, F., Murphy, B. (2020). Variable selection for robust model-based learning from contaminated data. In Pollice A, Salvati N, Schirripa Spagnolo F (a cura di), Book of Short Papers SIS 2020 (pp. 1117-1122). Pearson.

Variable selection for robust model-based learning from contaminated data

Cappozzo, A
Primo
;
Greselin, F
Secondo
;
2020

Abstract

Several contributions to the recent literature have shown that supervised learning is greatly enhanced when only the most relevant features are selected for building the discrimination rule. Unfortunately, outliers and wrongly labelled units may undermine the determination of relevant predictors, and almost no dedicated methodologies have been developed to face this issue. In the present paper, we introduce a new robust variable selection approach, that embeds a classifier within a greedy-forward procedure. An experiment on synthetic data is provided, to under- line the benefits of the proposed method in comparison with non-robust solutions.
Capitolo o saggio
Variable Selection, Model-Based Classification, Label Noise, Outliers Detection, Wrapper approach, Impartial Trimming, Robust Estimation
English
Book of Short Papers SIS 2020
9788891910776
Cappozzo, A., Greselin, F., Murphy, B. (2020). Variable selection for robust model-based learning from contaminated data. In Pollice A, Salvati N, Schirripa Spagnolo F (a cura di), Book of Short Papers SIS 2020 (pp. 1117-1122). Pearson.
Cappozzo, A; Greselin, F; Murphy, B
File in questo prodotto:
File Dimensione Formato  
SIS2020 CGM Robust variable selection REV.pdf

accesso aperto

Descrizione: Articolo Principale
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 145.07 kB
Formato Adobe PDF
145.07 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/290338
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact