Neural Variational Dropout Processes
This work addresses the problem of robust meta-learning for researchers and practitioners in machine learning, offering a novel method for few-shot learning, though it appears incremental as it builds on existing dropout and variational inference techniques.
The paper tackles robust meta-learning by introducing Neural Variational Dropout Processes (NVDPs), a Bayesian approach that models conditional posterior distributions using task-specific dropout for efficient few-shot learning, achieving excellent performance in tasks like 1D stochastic regression, image inpainting, and classification.
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.