# Uncertainty in Model-Agnostic Meta-Learning using Variational Inference

arXiv: https://arxiv.org/abs/1907.11864 · HTML: https://mlsanity.com/paper/1907.11864/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2019.

## Built on by (most cited first, 23 of 23)

- [Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification](https://mlsanity.com/paper/2110.14012/) (2021)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [HyperShot: Few-Shot Learning by Kernel HyperNetworks](https://mlsanity.com/paper/2203.11378/) (2022)
- [The Neural Process Family: Survey, Applications and Perspectives](https://mlsanity.com/paper/2209.00517/) (2022)
- [HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks](https://mlsanity.com/paper/2205.15745/) (2022)
- [Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Prediction](https://mlsanity.com/paper/2210.03067/) (2022)
- [Is Bayesian Model-Agnostic Meta Learning Better than Model-Agnostic Meta Learning, Provably?](https://mlsanity.com/paper/2203.03059/) (2022)
- [Information-Theoretic Analysis of Epistemic Uncertainty in Bayesian Meta-learning](https://mlsanity.com/paper/2106.00252/) (2021)
- [Multidimensional Belief Quantification for Label-Efficient Meta-Learning](https://mlsanity.com/paper/2203.12768/) (2022)
- [Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes](https://mlsanity.com/paper/2302.11709/) (2023)
- [Similarity of Classification Tasks](https://mlsanity.com/paper/2101.11201/) (2021)
- [Transductive Decoupled Variational Inference for Few-Shot Classification](https://mlsanity.com/paper/2208.10559/) (2022)
- [Probabilistic task modelling for meta-learning](https://mlsanity.com/paper/2106.04802/) (2021)
- [Scalable Bayesian Meta-Learning through Generalized Implicit Gradients](https://mlsanity.com/paper/2303.17768/) (2023)
- [Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization](https://mlsanity.com/paper/2108.00785/) (2021)
- [Task Weighting in Meta-learning with Trajectory Optimisation](https://mlsanity.com/paper/2301.01400/) (2023)
- [Neural Variational Dropout Processes](https://mlsanity.com/paper/2510.19425/) (2025)
- [GCCN: Global Context Convolutional Network](https://mlsanity.com/paper/2110.11664/) (2021)
- [Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning](https://mlsanity.com/paper/2110.13188/) (2021)
- [Learning by Examples Based on Multi-level Optimization](https://mlsanity.com/paper/2109.10824/) (2021)
- [Hypernetwork approach to Bayesian MAML](https://mlsanity.com/paper/2210.02796/) (2022)
- [A Hierarchical Bayesian Model for Deep Few-Shot Meta Learning](https://mlsanity.com/paper/2306.09702/) (2023)
- [Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasks](https://mlsanity.com/paper/2410.01476/) (2024)

## Abstract (arXiv)

We introduce a new, rigorously-formulated Bayesian meta-learning algorithm that learns a probability distribution of model parameter prior for few-shot learning. The proposed algorithm employs a gradient-based variational inference to infer the posterior of model parameters to a new task. Our algorithm can be applied to any model architecture and can be implemented in various machine learning paradigms, including regression and classification. We show that the models trained with our proposed meta-learning algorithm are well calibrated and accurate, with state-of-the-art calibration and classification results on two few-shot classification benchmarks (Omniglot and Mini-ImageNet), and competitive results in a multi-modal task-distribution regression.