# Fast Context Adaptation via Meta-Learning

arXiv: https://arxiv.org/abs/1810.03642 · HTML: https://mlsanity.com/paper/1810.03642/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2018.

## Built on by (most cited first, 8 of 8)

- [Learning Fast Sample Re-weighting Without Reward Data](https://mlsanity.com/paper/2109.03216/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Neural Relational Inference with Fast Modular Meta-learning](https://mlsanity.com/paper/2310.07015/) (2023)
- [Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile](https://mlsanity.com/paper/2206.01944/) (2022)
- [RotoGBML: Towards Out-of-Distribution Generalization for Gradient-Based Meta-Learning](https://mlsanity.com/paper/2303.06679/) (2023)
- [Improving Generalization via Meta-Learning on Hard Samples](https://mlsanity.com/paper/2403.12236/) (2024)
- [Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts](https://mlsanity.com/paper/2403.08477/) (2024)
- [Improving Meta-Learning Generalization with Activation-Based Early-Stopping](https://mlsanity.com/paper/2208.02377/) (2022)

## Abstract (arXiv)

We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared parameters that are meta-trained and shared across tasks. At test time, only the context parameters are updated, leading to a low-dimensional task representation. We show empirically that CAVIA outperforms MAML for regression, classification, and reinforcement learning. Our experiments also highlight weaknesses in current benchmarks, in that the amount of adaptation needed in some cases is small.