arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10417cs.LGstat.ML
收藏

基于One-vs-Each Pólya-Gamma增广高斯过程的贝叶斯Few-Shot分类

Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes

Vector Institute, University of Toronto(向量研究所,多伦多大学)

Jake Snell, Richard Zemel

摘要:

Few-Shot分类(FSC)是在给定小的标记数据集的情况下使分类器适应看不见的类的任务,是迈向类人机器学习的重要一步。贝叶斯方法非常适合解决在Few-Shot场景中过度拟合的基本问题,因为它们允许从业者指定先验信念并根据观察到的数据更新这些信念。当代的贝叶斯Few-Shot分类方法保持了模型参数的后验分布,这很慢,并且需要随模型大小而扩展的存储。相反,我们提出了一个基于Pólya-Gamma增强和one-vs-each softmax近似的新组合的高斯过程分类器,使我们能够有效地边缘化函数而不是模型参数。我们证明了改进的准确性和不确定性量化标准的Few-Shot分类基准和Few-Shot域转移任务。

英文摘要:

Few-shot classification (FSC), the task of adapting a classifier to unseen classes given a small labeled dataset, is an important step on the path toward human-like machine learning. Bayesian methods are well-suited to tackling the fundamental issue of overfitting in the few-shot scenario because they allow practitioners to specify prior beliefs and update those beliefs in light of observed data. Contemporary approaches to Bayesian few-shot classification maintain a posterior distribution over model parameters, which is slow and requires storage that scales with model size. Instead, we propose a Gaussian process classifier based on a novel combination of Pólya-Gamma augmentation and the one-vs-each softmax approximation that allows us to efficiently marginalize over functions rather than model parameters. We demonstrate improved accuracy and uncertainty quantification on both standard few-shot classification benchmarks and few-shot domain transfer tasks.

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。

↑