Insu Jeon

TL;DR: In this article, an intermediate stochastic layer of the generator is leveraged to constrain the mutual information between the input and the generated output, which can harness the latent space in a disentangled and interpretable manner.

TL;DR: This paper presents a new Bayesian meta-learning approach called Neural Variational Dropout Processes (NVDPs), which enables the robust approximation of task-specific dropout rates that can deal with a wide range of functional ambiguities and uncertainties.

Abstract: 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 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.