Work

Hypernetwork Approach to Bayesian MAML (Student Abstract)

Year: 2025

Type: conference-paper

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). 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.

Source: Proceedings of the AAAI Conference on Artificial Intelligence

DOI: 10.1609/aaai.v39i28.35239

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

Institution: Jagiellonian University

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

Funder: European Commission

Award: Postdoctoral Fellowships in Poland to Boost International Mobility and Skills Training