Neural Variational Dropout Processes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jeon, Insu, Park, Youngjin, Kim, Gunhee
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914107806973952
author Jeon, Insu
Park, Youngjin
Kim, Gunhee
author_facet Jeon, Insu
Park, Youngjin
Kim, Gunhee
contents Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs). NVDPs model the conditional posterior distribution based on a task-specific dropout; a low-rank product of Bernoulli experts meta-model is utilized for a memory-efficient mapping of dropout rates from a few observed contexts. It allows for a quick reconfiguration of a globally learned and shared neural network for new tasks in multi-task few-shot learning. In addition, NVDPs utilize a novel prior conditioned on the whole task data to optimize the conditional \textit{dropout} posterior in the amortized variational inference. Surprisingly, this enables the robust approximation of task-specific dropout rates that can deal with a wide range of functional ambiguities and uncertainties. We compared the proposed method with other meta-learning approaches in the few-shot learning tasks such as 1D stochastic regression, image inpainting, and classification. The results show the excellent performance of NVDPs.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19425
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Variational Dropout Processes
Jeon, Insu
Park, Youngjin
Kim, Gunhee
Machine Learning
Artificial Intelligence
68T07 (Artificial neural networks), 62F15 (Bayesian inference)
Learning to infer the conditional posterior model is a key step for robust meta-learning. This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs). NVDPs model the conditional posterior distribution based on a task-specific dropout; a low-rank product of Bernoulli experts meta-model is utilized for a memory-efficient mapping of dropout rates from a few observed contexts. It allows for a quick reconfiguration of a globally learned and shared neural network for new tasks in multi-task few-shot learning. In addition, NVDPs utilize a novel prior conditioned on the whole task data to optimize the conditional \textit{dropout} posterior in the amortized variational inference. Surprisingly, this enables the robust approximation of task-specific dropout rates that can deal with a wide range of functional ambiguities and uncertainties. We compared the proposed method with other meta-learning approaches in the few-shot learning tasks such as 1D stochastic regression, image inpainting, and classification. The results show the excellent performance of NVDPs.
title Neural Variational Dropout Processes
topic Machine Learning
Artificial Intelligence
68T07 (Artificial neural networks), 62F15 (Bayesian inference)
url https://arxiv.org/abs/2510.19425