# MetaFun: Meta-Learning with Iterative Functional Updates

arXiv: https://arxiv.org/abs/1912.02738 · HTML: https://mlsanity.com/paper/1912.02738/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2019.

## Built on by (most cited first, 30 of 34)

- [A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2205.06743/) (2022)
- [Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling](https://mlsanity.com/paper/2207.04179/) (2022)
- [Rectifying the Shortcut Learning of Background for Few-Shot Learning](https://mlsanity.com/paper/2107.07746/) (2021)
- [A Closer Look at Few-shot Classification Again](https://mlsanity.com/paper/2301.12246/) (2023)
- [Few-Shot Diffusion Models](https://mlsanity.com/paper/2205.15463/) (2022)
- [Online Adaptation of Language Models with a Memory of Amortized Contexts](https://mlsanity.com/paper/2403.04317/) (2024)
- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [Group Equivariant Conditional Neural Processes](https://mlsanity.com/paper/2102.08759/) (2021)
- [Neural Processes with Stochastic Attention: Paying more attention to the context dataset](https://mlsanity.com/paper/2204.05449/) (2022)
- [Non-Gaussian Gaussian Processes for Few-Shot Regression](https://mlsanity.com/paper/2110.13561/) (2021)
- [Learning to Rectify for Robust Learning with Noisy Labels](https://mlsanity.com/paper/2111.04239/) (2021)
- [Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice](https://mlsanity.com/paper/2211.07206/) (2022)
- [MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics](https://mlsanity.com/paper/2301.12095/) (2023)
- [Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition](https://mlsanity.com/paper/2408.00249/) (2024)
- [Deep Stochastic Processes via Functional Markov Transition Operators](https://mlsanity.com/paper/2305.15574/) (2023)
- [SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation](https://mlsanity.com/paper/2110.12279/) (2021)
- [Few-shot Learning for Topic Modeling](https://mlsanity.com/paper/2104.09011/) (2021)
- [Meta-learning of Physics-informed Neural Networks for Efficiently Solving Newly Given PDEs](https://mlsanity.com/paper/2310.13270/) (2023)
- [Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder](https://mlsanity.com/paper/2310.16318/) (2023)
- [Spectral Convolutional Conditional Neural Processes](https://mlsanity.com/paper/2404.13182/) (2024)
- [Curvature Learning for Generalization of Hyperbolic Neural Networks](https://mlsanity.com/paper/2508.17232/) (2025)
- [Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximation](https://mlsanity.com/paper/2111.05392/) (2021)
- [Meta-learning of semi-supervised learning from tasks with heterogeneous attribute spaces](https://mlsanity.com/paper/2311.05088/) (2023)
- [Context-Aware Multimodal Pretraining](https://mlsanity.com/paper/2411.15099/) (2024)
- [Meta-free few-shot learning via representation learning with weight averaging](https://mlsanity.com/paper/2204.12466/) (2022)
- [Meta-Learning for Koopman Spectral Analysis with Short Time-series](https://mlsanity.com/paper/2102.04683/) (2021)
- [Meta-learning for Matrix Factorization without Shared Rows or Columns](https://mlsanity.com/paper/2106.15133/) (2021)
- [Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module](https://mlsanity.com/paper/2112.07222/) (2021)
- [BaseTransformers: Attention over base data-points for One Shot Learning](https://mlsanity.com/paper/2210.02476/) (2022)
- [Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection](https://mlsanity.com/paper/2103.00684/) (2021)

## Abstract (arXiv)

We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gradient descent which iteratively improves the representation. The final representation is used to condition the decoder to make predictions on unlabeled data. Our approach is the first to demonstrates the success of encoder-decoder style meta-learning methods like conditional neural processes on large-scale few-shot classification benchmarks such as miniImageNet and tieredImageNet, where it achieves state-of-the-art performance.