Learning to Transfer: A Foliated Theory
This work provides a theoretical foundation for transfer learning, addressing a core problem in machine learning for improving efficiency and generalization.
The paper tackles the lack of a foundational description for learning to transfer by introducing a framework based on differential geometric foliation theory, which defines task relationships and enables constructive exploitation without specifying experimental results.
Learning to transfer considers learning solutions to tasks in a such way that relevant knowledge can be transferred from known task solutions to new, related tasks. This is important for general learning, as well as for improving the efficiency of the learning process. While techniques for learning to transfer have been studied experimentally, we still lack a foundational description of the problem that exposes what related tasks are, and how relationships between tasks can be exploited constructively. In this work, we introduce a framework using the differential geometric theory of foliations that provides such a foundation.