Hypernetwork approach to Bayesian MAML

Piotr Borycki, Piotr Kubacki, Marcin Przewięźlikowski, Tomasz Kuśmierczyk, Jacek Tabor, Przemysław Spurek

Keywords: few-shot learnirng, MAML, hypernetworks

TL;DR: n this paper we propose a novel generalization of Bayesian MAML, which employs Bayesian principles along with Hypernetworks for MAML.

Abstract:

The main goal of Few-Shot learning algorithms is to enable learning from small amounts of data. One of the most popular and elegant Few-Shot learning approaches is Model-Agnostic Meta-Learning (MAML). The main idea behind this method is to learn shared universal weights of a meta-model, which then are adapted for specific tasks. However, due to limited data size, the method suffers from overfitting and poorly quantifies uncertainty. Bayesian approaches could, in principle, alleviate these shortcomings by learning weight distributions in place of point-wise weights. Unfortunately, previous Bayesian modifications of MAML are limited in a way similar to the classic MAML, e.g., task-specific adaptations must share the same structure and can not diverge much from the universal meta-model. Additionally, task-specific distributions are considered posteriors to the universal distributions working as priors, and optimizing them jointly with gradients is hard and poses a risk of getting stuck in local optima.

In this paper, we propose BH-MAML, a novel Bayesian MAML generalization that employs Bayesian principles and Hypernetworks for MAML. We achieve better convergence than the previous methods by classically learning universal weights. Furthermore, Bayesian treatment of the specific tasks enables uncertainty quantification, and high flexibility of task adaptations is achieved using Hypernetworks instead of gradient-based updates. Consequently, the proposed approach not only improves over the previous methods, both classic and Bayesian MAML in several standard Few-Shot learning benchmarks but also benefits from the properties of the Bayesian framework.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Probabilistic Methods (eg, variational inference, causal inference, Gaussian processes)

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2210.02796/code)