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

arXiv: https://arxiv.org/abs/2010.01992 · HTML: https://mlsanity.com/paper/2010.01992/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Context-Aware Meta-Learning](https://mlsanity.com/paper/2310.10971/) (2023)
- [Cap2Aug: Caption guided Image to Image data Augmentation](https://mlsanity.com/paper/2212.05404/) (2022)
- [In-Context Learning for Few-Shot Molecular Property Prediction](https://mlsanity.com/paper/2310.08863/) (2023)
- [Few-shot Classification via Ensemble Learning with Multi-Order Statistics](https://mlsanity.com/paper/2305.00454/) (2023)
- [Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition](https://mlsanity.com/paper/2401.07061/) (2024)
- [FewTopNER: Integrating Few-Shot Learning with Topic Modeling and Named Entity Recognition in a Multilingual Framework](https://mlsanity.com/paper/2502.02391/) (2025)
- [Episodic-free Task Selection for Few-shot Learning](https://mlsanity.com/paper/2402.00092/) (2024)

## Abstract (arXiv)

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.