Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs. Curriculum learning strategies have been successfully employed in all areas of machine learning, in a wide range of tasks. However, the necessity of finding a way to rank the samples from easy to hard, as well as the right pacing function for introducing more difficult data can limit the usage of the curriculum approaches. In this survey, we show how these limits have been tackled in the literature, and we present different curriculum learning instantiations for various tasks in machine learning. We construct a multi-perspective taxonomy of curriculum learning approaches by hand, considering various classification criteria. We further build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm, linking the discovered clusters with our taxonomy. At the end, we provide some interesting directions for future work.

Curriculum Learning: A Survey / Soviany, P.; Ionescu, R. T.; Rota, P.; Sebe, N.. - In: INTERNATIONAL JOURNAL OF COMPUTER VISION. - ISSN 0920-5691. - 130:6(2022), pp. 1526-1565. [10.1007/s11263-022-01611-x]

Curriculum Learning: A Survey

Rota P.;Sebe N.
2022-01-01

Abstract

Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs. Curriculum learning strategies have been successfully employed in all areas of machine learning, in a wide range of tasks. However, the necessity of finding a way to rank the samples from easy to hard, as well as the right pacing function for introducing more difficult data can limit the usage of the curriculum approaches. In this survey, we show how these limits have been tackled in the literature, and we present different curriculum learning instantiations for various tasks in machine learning. We construct a multi-perspective taxonomy of curriculum learning approaches by hand, considering various classification criteria. We further build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm, linking the discovered clusters with our taxonomy. At the end, we provide some interesting directions for future work.
2022
6
Soviany, P.; Ionescu, R. T.; Rota, P.; Sebe, N.
Curriculum Learning: A Survey / Soviany, P.; Ionescu, R. T.; Rota, P.; Sebe, N.. - In: INTERNATIONAL JOURNAL OF COMPUTER VISION. - ISSN 0920-5691. - 130:6(2022), pp. 1526-1565. [10.1007/s11263-022-01611-x]
File in questo prodotto:
File Dimensione Formato  
2101.10382.pdf

Solo gestori archivio

Tipologia: Pre-print non referato (Non-refereed preprint)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.46 MB
Formato Adobe PDF
4.46 MB Adobe PDF   Visualizza/Apri
s11263-022-01611-x.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.92 MB
Formato Adobe PDF
1.92 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/11572/357785
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 98
  • ???jsp.display-item.citation.isi??? 60
social impact