Published August 5, 2025 | Version v1
Conference proceeding Open

Hypernetwork Approach to Bayesian MAML (Student Abstract)

Description

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). In this paper, we propose a novel framework for Bayesian MAML called BH-MAML, which employs Hypernetworks for weight updates. It learns the universal weights point-wise, but a probabilistic structure is added when adapted for specific tasks. In such a framework, we can use simple Gaussian distributions or more complicated posteriors induced by Continuous Normalizing Flows.

Files

main_AAAI.pdf

Files (829.5 kB)

Name Size Download all
md5:091d58b94e03889cd6cdd7376b4343ec
829.5 kB Preview Download

Additional details