Transfer Learning by Learning Projections from Target to Source
Résumé
Using transfer learning to help in solving a new classification task where labeled data is scarce is becoming popular. Numerous experiments with deep neural networks, where the representation learned on a source task is transferred to learn a target neural network, have shown the benefits of the approach. This paper, similarly, deals with hypothesis transfer learning. However, it presents a new approach where, instead of transferring a representation, the source hypothesis is kept and this is a translation from the target domain to the source domain that is learned. In a way, a change of representation is learned. We show how this method performs very well on a classification of time series task where the space of time series is changed between source and target.
Domaines
Apprentissage [cs.LG]
Fichier principal
Cornuéjols2020_Chapter_TransferLearningByLearningProj.pdf (2.69 Mo)
Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte