论文标题
SOQAL：选择性甲骨文提出基于一致性的心脏信号的主动学习
SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals
论文作者
论文摘要
临床设置通常以丰富的未标记数据和有限的标记数据为特征。这通常是由载于甲壳（例如医师）提供注释的高负担驱动的。减轻这种负担的一种方法是通过积极学习（AL），涉及（a）获取和（b）信息无标记的实例的注释。尽管以前的工作独立解决了这些要素之一，但我们提出了一个解决这两者的框架。为了获得，我们建议按一致性（BALC）（BALC）进行贝叶斯主动学习，这是一个子框架，它既散布实例和网络参数，又量化了网络输出概率分布的变化。对于注释，我们提出了Soqal，这是一种动态确定每个获取未标记的实例的子框架，从Oracle请求标签或对其进行伪标签。我们表明，即使在存在嘈杂的甲骨文的情况下，BALC也可以胜过诸如秃头之类的开始启动采集功能，而Soqal的表现也优于基线方法。
Clinical settings are often characterized by abundant unlabelled data and limited labelled data. This is typically driven by the high burden placed on oracles (e.g., physicians) to provide annotations. One way to mitigate this burden is via active learning (AL) which involves the (a) acquisition and (b) annotation of informative unlabelled instances. Whereas previous work addresses either one of these elements independently, we propose an AL framework that addresses both. For acquisition, we propose Bayesian Active Learning by Consistency (BALC), a sub-framework which perturbs both instances and network parameters and quantifies changes in the network output probability distribution. For annotation, we propose SoQal, a sub-framework that dynamically determines whether, for each acquired unlabelled instance, to request a label from an oracle or to pseudo-label it instead. We show that BALC can outperform start-of-the-art acquisition functions such as BALD, and SoQal outperforms baseline methods even in the presence of a noisy oracle.
