Improving Few-Shot Learning through Multi-task Representation Learning Theory

Abstract: 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.

For attribution in academic contexts, please cite this work as

“Improving Few-Shot Learning through Multi-task Representation Learning Theory” Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard. Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XX. Cham: Springer Nature Switzerland, 2022.

@inproceedings{bouniot2022improving,
 title={Improving Few-Shot Learning Through Multi-task Representation Learning Theory},
 author={Bouniot, Quentin and Redko, Ievgen and Audigier, Romaric and Loesch, Ang{\'e}lique and Habrard, Amaury},
 booktitle={Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XX},
 pages={435--452},
 year={2022},
 organization={Springer}
}