Semi-supervised learning has shown its potential in many real-world applications where only few labeled examples are available. However, when some fairness constraints need to be satisfied, semi-supervised classification models often struggle as they are required to cope with the lack of sufficient information for predicting the target variable while forgetting its relationships with any sensitive and potentially discriminatory attribute. To address this issue, we propose a fair semi-supervised representation learning architecture that leads to fair and accurate classification results even in very challenging scenarios with few labeled (but biased) instances. We show experimentally that our model can be easily adopted in very general settings, as the learned representations may be employed to train any supervised classifier. Moreover, when applied to several synthetic and real-world datasets, our method is competitive with state-of-the-art fair semi-supervised approaches.

FairSwiRL: fair semi-supervised classification with representation learning

Yang, Shuyi
Co-first
;
Cerrato, Mattia
Co-first
;
Ienco, Dino;Pensa, Ruggero G.
Co-last
;
Esposito, Roberto
Co-last
2023-01-01

Abstract

Semi-supervised learning has shown its potential in many real-world applications where only few labeled examples are available. However, when some fairness constraints need to be satisfied, semi-supervised classification models often struggle as they are required to cope with the lack of sufficient information for predicting the target variable while forgetting its relationships with any sensitive and potentially discriminatory attribute. To address this issue, we propose a fair semi-supervised representation learning architecture that leads to fair and accurate classification results even in very challenging scenarios with few labeled (but biased) instances. We show experimentally that our model can be easily adopted in very general settings, as the learned representations may be employed to train any supervised classifier. Moreover, when applied to several synthetic and real-world datasets, our method is competitive with state-of-the-art fair semi-supervised approaches.
2023
112
9
3051
3076
https://link.springer.com/article/10.1007/s10994-023-06342-9
semi-supervised autoencoder, fairness, deep neural networks
Yang, Shuyi; Cerrato, Mattia; Ienco, Dino; Pensa, Ruggero G.; Esposito, Roberto
File in questo prodotto:
File Dimensione Formato  
ml2023_online.pdf

Accesso aperto

Descrizione: PDF open online
Tipo di file: PDF EDITORIALE
Dimensione 1.72 MB
Formato Adobe PDF
1.72 MB Adobe PDF Visualizza/Apri
ml2023_printed.pdf

Accesso aperto

Descrizione: PDF a stampa
Tipo di file: PDF EDITORIALE
Dimensione 1.73 MB
Formato Adobe PDF
1.73 MB 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/2318/1915252
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact