data imbalance, in which a plurality of the data samples come from a small
proportion of labels, poses a challenge in training deep neural networks.
Unlike classification, in regression the labels are continuous,
提出了 SIMILAR (Submodular Information Measures based actIve LeARning)—— 利用最近提出的子模信息度量 (SIM) 作为获取函数的统一主动学习框架,既能在标准主动学习中工作,也可以轻松扩展到考虑上述实际情况,并作为可伸缩到大型实际数据集的主动学习一站式解决方案。