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 \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.
Abstract (translated)
学习推断条件后验模型是鲁棒元学习的关键步骤。本文提出了一种新的贝叶斯元学习方法，称为神经变分Dropout过程（Neural Variational Dropout Processes，NVDP）。NVDP基于任务特定的dropout来建模条件后验分布；采用低秩伯努利专家元模型的乘积，以记忆高效的方式从少数观察到的情境中映射dropout率。这使得能够快速重新配置一个全局学习并共享的神经网络，以便为多任务少样本学习中的新任务进行调整。 此外，NVDP使用了一种新颖的任务数据整体条件下的先验，在近似变分推理中优化条件*dropout*后验。令人惊讶的是，这种方法能够鲁棒地逼近处理各种功能性模糊性和不确定性的情况下特定任务的dropout率。 我们将在1D随机回归、图像修复和分类等少样本学习任务上，将所提出的方法与其他元学习方法进行了比较。结果显示NVDPs具有出色的性能。
URL
https://arxiv.org/abs/2510.19425
