Learning from fuzzy labels (LFL) refers to a generalization of supervised learning in which supervision is represented as a (epistemic) fuzzy set over the collection of possible classification labels: this represents the uncertainty of the annotating agent with respect to the true class label to be assigned to the data instances, using a possibility distribution. The two most popular LFL algorithmic approaches are either based on generalized risk minimization (GRM) or nearest-neighbor (NN) methods: while both methods have been applied successfully with promising empirical results, theoretical characterizations of these approaches, in the framework of learning theory, have been lacking. In this article we address this gap and study the LFL problem from the perspective of statistical learning theory, providing a theoretical analysis of both GRM and NN, in terms of sample complexity and risk bounds.

Campagner, A. (2021). Learnability in “Learning from Fuzzy Labels”. In 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (pp.1-6). Institute of Electrical and Electronics Engineers Inc. [10.1109/FUZZ45933.2021.9494534].

Learnability in “Learning from Fuzzy Labels”

Campagner, Andrea
2021

Abstract

Learning from fuzzy labels (LFL) refers to a generalization of supervised learning in which supervision is represented as a (epistemic) fuzzy set over the collection of possible classification labels: this represents the uncertainty of the annotating agent with respect to the true class label to be assigned to the data instances, using a possibility distribution. The two most popular LFL algorithmic approaches are either based on generalized risk minimization (GRM) or nearest-neighbor (NN) methods: while both methods have been applied successfully with promising empirical results, theoretical characterizations of these approaches, in the framework of learning theory, have been lacking. In this article we address this gap and study the LFL problem from the perspective of statistical learning theory, providing a theoretical analysis of both GRM and NN, in terms of sample complexity and risk bounds.
paper
Fuzzy Labels; Learning Theory; Nearest Neighbors; Risk Minimization;
English
2021 IEEE CIS International Conference on Fuzzy Systems, FUZZ 2021 - 11 July 2021 through 14 July 2021
2021
2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
978-166544407-1
2021
2021-July
1
6
reserved
Campagner, A. (2021). Learnability in “Learning from Fuzzy Labels”. In 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (pp.1-6). Institute of Electrical and Electronics Engineers Inc. [10.1109/FUZZ45933.2021.9494534].
File in questo prodotto:
File Dimensione Formato  
Learnability_in_Learning_from_Fuzzy_Labels.pdf

Solo gestori archivio

Descrizione: articolo
Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 556.5 kB
Formato Adobe PDF
556.5 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/10281/327394
Citazioni
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 1
Social impact