Google Research

What is being transferred in transfer learning?

NeurIPS (2020) (to appear)

Abstract

One desired capability for machines is the ability to transfer their understanding of one domain to another domain where data is (usually) scarce. Despite ample adaptation of transfer learning in many deep learning applications, we yet do not understand what enables a successful transfer and which part of the network is responsible for that. In this paper, we provide new tools and analysis to address these fundamental questions. We separate the effect of feature reuse from learning high-level statistics of data and show that some benefit of transfer learning comes from the latter.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work