# Weighted Meta-Learning

arXiv: https://arxiv.org/abs/2003.09465 · HTML: https://mlsanity.com/paper/2003.09465/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2020.

## Built on by (most cited first, 2 of 2)

- [For high-dimensional hierarchical models, consider exchangeability of effects across covariates instead of across datasets](https://mlsanity.com/paper/2107.06428/) (2021)
- [Task Weighting in Meta-learning with Trajectory Optimisation](https://mlsanity.com/paper/2301.01400/) (2023)

## Abstract (arXiv)

Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-learning algorithms, such as model-agnostic meta-learning (MAML), only assume access to the target samples for fine-tuning. In this work, we provide a general framework for meta-learning based on weighting the loss of different source tasks, where the weights are allowed to depend on the target samples. In this general setting, we provide upper bounds on the distance of the weighted empirical risk of the source tasks and expected target risk in terms of an integral probability metric (IPM) and Rademacher complexity, which apply to a number of meta-learning settings including MAML and a weighted MAML variant. We then develop a learning algorithm based on minimizing the error bound with respect to an empirical IPM, including a weighted MAML algorithm, α-MAML. Finally, we demonstrate empirically on several regression problems that our weighted meta-learning algorithm is able to find better initializations than uniformly-weighted meta-learning algorithms, such as MAML.