Transferring Knowledge across Learning Processes
This addresses the challenge of effective transfer learning for AI systems in diverse domains, though it appears incremental as it builds on existing meta-learning and transfer learning concepts.
The paper tackles the problem of transferring knowledge in complex scenarios where tasks are not tightly linked, by proposing Leap, a framework that transfers knowledge across learning processes, and demonstrates it outperforms competing methods on computer vision tasks and scales to demanding reinforcement learning environments like Atari.
In complex transfer learning scenarios new tasks might not be tightly linked to previous tasks. Approaches that transfer information contained only in the final parameters of a source model will therefore struggle. Instead, transfer learning at a higher level of abstraction is needed. We propose Leap, a framework that achieves this by transferring knowledge across learning processes. We associate each task with a manifold on which the training process travels from initialization to final parameters and construct a meta-learning objective that minimizes the expected length of this path. Our framework leverages only information obtained during training and can be computed on the fly at negligible cost. We demonstrate that our framework outperforms competing methods, both in meta-learning and transfer learning, on a set of computer vision tasks. Finally, we demonstrate that Leap can transfer knowledge across learning processes in demanding reinforcement learning environments (Atari) that involve millions of gradient steps.