Learning What and Where to Transfer

TL;DR

This paper introduces a meta-learning based transfer learning method that automatically determines what knowledge to transfer and where in the network to improve performance, reducing manual tuning.

Contribution

It proposes a novel meta-learning framework that automatically learns transfer configurations between heterogeneous networks, outperforming hand-crafted methods.

Findings

Meta-transfer significantly outperforms prior methods.

Automated scheme reduces manual configuration.

Effective across various datasets and architectures.

Abstract

As the application of deep learning has expanded to real-world problems with insufficient volume of training data, transfer learning recently has gained much attention as means of improving the performance in such small-data regime. However, when existing methods are applied between heterogeneous architectures and tasks, it becomes more important to manage their detailed configurations and often requires exhaustive tuning on them for the desired performance. To address the issue, we propose a novel transfer learning approach based on meta-learning that can automatically learn what knowledge to transfer from the source network to where in the target network. Given source and target networks, we propose an efficient training scheme to learn meta-networks that decide (a) which pairs of layers between the source and target networks should be matched for knowledge transfer and (b) which features and how much knowledge from each feature should be transferred. We validate our meta-transfer approach against recent transfer learning methods on various datasets and network architectures, on which our automated scheme significantly outperforms the prior baselines that find "what and where to transfer" in a hand-crafted manner.