Improving Few-Shot Learning through Multi-task Representation Learning Theory
This work addresses the challenge of sample efficiency in few-shot learning for machine learning practitioners, though it is incremental as it builds on existing theory to refine methods.
The paper tackles the problem of few-shot learning by applying multi-task representation learning theory to analyze and improve meta-learning algorithms, resulting in a new spectral-based regularization term that enhances performance on few-shot classification benchmarks.
In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task. We start by reviewing recent advances in MTR theory and show that they can provide novel insights for popular meta-learning algorithms when analyzed within this framework. In particular, we highlight a fundamental difference between gradient-based and metric-based algorithms in practice and put forward a theoretical analysis to explain it. Finally, we use the derived insights to improve the performance of meta-learning methods via a new spectral-based regularization term and confirm its efficiency through experimental studies on few-shot classification benchmarks. To the best of our knowledge, this is the first contribution that puts the most recent learning bounds of MTR theory into practice for the task of few-shot classification.