On the Role of the Source Dataset in Transfer Learning
Author(s)
Khaddaj, Alaa
DownloadThesis PDF (4.802Mb)
Advisor
Madry, Aleksander
Terms of use
Metadata
Show full item recordAbstract
It is commonly believed that in transfer learning including more pre-training data translates into better performance. However, recent evidence suggests that removing data from the source dataset can actually help too. In this work, we take a closer look at the role of the source dataset's composition in transfer learning and present a framework for probing its impact on downstream performance. Our framework gives rise to new capabilities such as pinpointing transfer learning brittleness as well as detecting pathologies such as data-leakage and the presence of misleading examples in the source dataset. In particular, we demonstrate that removing detrimental datapoints identified by our framework improves transfer learning performance from ImageNet on a variety of target tasks.
Date issued
2022-09Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology