[HTML][HTML] FairSwiRL: fair semi-supervised classification with representation learning

S Yang, M Cerrato, D Ienco, RG Pensa, R Esposito - Machine Learning, 2023 - Springer
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 …

FairSwiRL: fair semi-supervised classification with representation learning

S Yang, M Cerrato, D Ienco, RG Pensa, R Esposito - Machine Learning, 2023 - dl.acm.org
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 …

[PDF][PDF] FairSwiRL: fair semi‑supervised classification with representation learning

S Yang, M Cerrato, D Ienco, RG Pensa, R Esposito - 2023 - researchgate.net
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 …

FairSwiRL: fair semi-supervised classification with representation learning

S Yang, M Cerrato, D Ienco, RG Pensa, R Esposito - Mach. Learn., 2023 - openreview.net
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 …

[PDF][PDF] FairSwiRL: fair semi‑supervised classification with representation learning

S Yang, M Cerrato, D Ienco, RG Pensa, R Esposito - Machine Learning, 2023 - iris.unito.it
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 …

[PDF][PDF] FairSwiRL: fair semi‑supervised classification with representation learning

S Yang, M Cerrato, D Ienco, RG Pensa, R Esposito - Machine Learning, 2023 - iris.unito.it
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 …