2018/12/03 by Sebastian Flennerhag, Flennerhag, Sebastian, Pablo García Moreno +5 · 3 citations
Psychology · Social Sciences · #Artificial Intelligence (cs.AI) #Education and Critical Thinking Development #FOS: Computer and information sciences #Higher Education Learning Practices #Innovative Teaching and Learning Methods #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.1812.01054
openalex publication_date 2018/12/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.