# Learning to Transfer

arXiv: https://arxiv.org/abs/1708.05629 · HTML: https://mlsanity.com/paper/1708.05629/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2017.

## Built on by (most cited first, 3 of 3)

- [Pre-training on Synthetic Driving Data for Trajectory Prediction](https://mlsanity.com/paper/2309.10121/) (2023)
- [A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos](https://mlsanity.com/paper/2103.15596/) (2021)
- [Towards Dynamic Feature Selection with Attention to Assist Banking Customers in Establishing a New Business](https://mlsanity.com/paper/2105.03852/) (2021)

## Abstract (arXiv)

Transfer learning borrows knowledge from a source domain to facilitate learning in a target domain. Two primary issues to be addressed in transfer learning are what and how to transfer. For a pair of domains, adopting different transfer learning algorithms results in different knowledge transferred between them. To discover the optimal transfer learning algorithm that maximally improves the learning performance in the target domain, researchers have to exhaustively explore all existing transfer learning algorithms, which is computationally intractable. As a trade-off, a sub-optimal algorithm is selected, which requires considerable expertise in an ad-hoc way. Meanwhile, it is widely accepted in educational psychology that human beings improve transfer learning skills of deciding what to transfer through meta-cognitive reflection on inductive transfer learning practices. Motivated by this, we propose a novel transfer learning framework known as Learning to Transfer (L2T) to automatically determine what and how to transfer are the best by leveraging previous transfer learning experiences. We establish the L2T framework in two stages: 1) we first learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer for a newly arrived pair of domains by optimizing the reflection function. Extensive experiments demonstrate the L2T's superiority over several state-of-the-art transfer learning algorithms and its effectiveness on discovering more transferable knowledge.