Gerace, Federica;
Saglietti, Luca;
Mannelli, Stefano Sarao;
Saxe, Andrew;
Zdeborova, Lenka;
(2022)
Probing transfer learning with a model of synthetic correlated datasets.
Machine Learning: Science and Technology
, 3
(1)
, Article 015030. 10.1088/2632-2153/ac4f3f.
Preview |
Text
Gerace_2022_Mach._Learn.__Sci._Technol._3_015030.pdf - Published Version Download (1MB) | Preview |
Abstract
Transfer learning can significantly improve the sample efficiency of neural networks, by exploiting the relatedness between a data-scarce target task and a data-abundant source task. Despite years of successful applications, transfer learning practice often relies on ad-hoc solutions, while theoretical understanding of these procedures is still limited. In the present work, we re-think a solvable model of synthetic data as a framework for modeling correlation between data-sets. This setup allows for an analytic characterization of the generalization performance obtained when transferring the learned feature map from the source to the target task. Focusing on the problem of training two-layer networks in a binary classification setting, we show that our model can capture a range of salient features of transfer learning with real data. Moreover, by exploiting parametric control over the correlation between the two data-sets, we systematically investigate under which conditions the transfer of features is beneficial for generalization.
| Type: | Article |
|---|---|
| Title: | Probing transfer learning with a model of synthetic correlated datasets |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1088/2632-2153/ac4f3f |
| Publisher version: | https://doi.org/10.1088/2632-2153%2Fac4f3f |
| Language: | English |
| Additional information: | This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third-party material in this article are included in the Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ |
| Keywords: | Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, Interdisciplinary Applications, Multidisciplinary Sciences, Computer Science, Science & Technology - Other Topics, transfer learning, correlated dataset, data modelling, statistical physics |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neurosci Unit |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10160777 |
Archive Staff Only
 |
View Item |
