arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.00691cs.LG
收藏

全局卷积神经过程

Global Convolutional Neural Processes

University of New South Wales(新南威尔士大学);University of Technology Sydney(悉尼科技大学);University of Queensland(昆士兰大学)

Xuesong Wang, Lina Yao, Xianzhi Wang, Hye-young Paik, Sen Wang

摘要:

处理机器学习模型中的不确定性的能力对它们的预测能力本身来说已经变得同等重要,如果不是更重要的话。例如,在大流行期间,政府政策和个人决策不断围绕不确定性做出。针对这一点,神经过程族(NPF)最近通过桥接高斯过程和神经网络来照亮具有不确定性的预测。潜神经过程是NPF的一个成员,被认为能够模拟某些点上的不确定性(局部不确定性)以及一般函数先验(全局不确定性)。尽管如此,一些关键问题仍然没有得到解决,例如全球不确定性的正式定义,全球不确定性背后的因果关系,以及生成模型对全球不确定性的操纵。关于这一点,我们建立了一个成员GloBal卷积神经过程(GBCoNP),它在潜在的NPF中实现了SOTA对数似然。它设计了一个全局不确定性表示p(z),它是离散输入空间上的一个聚合。讨论了全局不确定性程度与任务内多样性之间的因果关系。在各种场景下分析学习的先验知识,包括1D,2D和新提出的时空COVID数据集。我们对全局不确定性的操作不仅实现了生成所需的样本来解决少样本学习,而且还实现了对函数先验的概率评估。

英文摘要:

The ability to deal with uncertainty in machine learning models has become equally, if not more, crucial to their predictive ability itself. For instance, during the pandemic, governmental policies and personal decisions are constantly made around uncertainties. Targeting this, Neural Process Families (NPFs) have recently shone a light on prediction with uncertainties by bridging Gaussian processes and neural networks. Latent neural process, a member of NPF, is believed to be capable of modelling the uncertainty on certain points (local uncertainty) as well as the general function priors (global uncertainties). Nonetheless, some critical questions remain unresolved, such as a formal definition of global uncertainties, the causality behind global uncertainties, and the manipulation of global uncertainties for generative models. Regarding this, we build a member GloBal Convolutional Neural Process(GBCoNP) that achieves the SOTA log-likelihood in latent NPFs. It designs a global uncertainty representation p(z), which is an aggregation on a discretized input space. The causal effect between the degree of global uncertainty and the intra-task diversity is discussed. The learnt prior is analyzed on a variety of scenarios, including 1D, 2D, and a newly proposed spatial-temporal COVID dataset. Our manipulation of the global uncertainty not only achieves generating the desired samples to tackle few-shot learning, but also enables the probability evaluation on the functional priors.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑