# Revisiting Meta-Learning as Supervised Learning

arXiv: https://arxiv.org/abs/2002.00573 · HTML: https://mlsanity.com/paper/2002.00573/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2020.

## Built on by (most cited first, 14 of 14)

- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Continual Learning with Pre-Trained Models: A Survey](https://mlsanity.com/paper/2401.16386/) (2024)
- [Learning without Forgetting for Vision-Language Models](https://mlsanity.com/paper/2305.19270/) (2023)
- [Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration](https://mlsanity.com/paper/2312.05229/) (2023)
- [MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning](https://mlsanity.com/paper/2412.09441/) (2024)
- [Representation Learning for Tabular Data: A Comprehensive Survey](https://mlsanity.com/paper/2504.16109/) (2025)
- [Model Spider: Learning to Rank Pre-Trained Models Efficiently](https://mlsanity.com/paper/2306.03900/) (2023)
- [How to Train Your MAML to Excel in Few-Shot Classification](https://mlsanity.com/paper/2106.16245/) (2021)
- [Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech](https://mlsanity.com/paper/2111.04040/) (2021)
- [Bridge the Modality and Capability Gaps in Vision-Language Model Selection](https://mlsanity.com/paper/2403.13797/) (2024)
- [Few-Shot Learning with a Strong Teacher](https://mlsanity.com/paper/2107.00197/) (2021)
- [Uniform Sampling over Episode Difficulty](https://mlsanity.com/paper/2108.01662/) (2021)
- [Contextualizing Meta-Learning via Learning to Decompose](https://mlsanity.com/paper/2106.08112/) (2021)
- [Towards Enabling Meta-Learning from Target Models](https://mlsanity.com/paper/2104.03736/) (2021)

## Abstract (arXiv)

Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to compare and evaluate. In this paper, we aim to provide a principled, unifying framework by revisiting and strengthening the connection between meta-learning and traditional supervised learning. By treating pairs of task-specific data sets and target models as (feature, label) samples, we can reduce many meta-learning algorithms to instances of supervised learning. This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning. For example, we obtain a better understanding of generalization properties, and we can readily transfer well-understood techniques, such as model ensemble, pre-training, joint training, data augmentation, and even nearest neighbor based methods. We provide an intuitive analogy of these methods in the context of meta-learning and show that they give rise to significant improvements in model performance on few-shot learning.