.png){kind=icon}
返回
Novel regularization method for the class imbalance problem
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2021.115974.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In neural network models, obtaining a high-quality dataset is critical because they are generally reliant on training data. A common problem that occurs is class imbalance, in which models tend to be biased to the majority class when the training data is not balanced. To overcome this problem, we propose a novel regularization method that provides a penalty to the loss function, using two facets of the distribution of the model's output p((y) over cap vertical bar x): (1) skewed mean and (2) variance divergence between p((y) over cap vertical bar x is an element of D+) and p((y) over cap vertical bar x is an element of D_). The experimental results demonstrate that our methods consistently improve the performance on imbalanced datasets. Moreover, the combination of two regularization methods provides a substantial performance improvement on five sentence classification datasets and also an image classification dataset; notably, state-of-the-art performances are achieved on the WikiQA and SelQA datasets.
Keyword:
Regularization
Class imbalance
Sentence classification
Image classification
期刊
IF:
7.5
论文数:
3.0W
被引数:
10.2W
机构
引用论文
.png){kind=icon}
The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance使用秩来避免方差分析中隐含的正态性假设
PREAI
分享收藏CNC-Pincer Rare-Earth Metal Amido Complexes with a Diarylamido Linked Biscarbene Ligand: Synthesis, Characterization, and Catalytic Activity具有二芳基酰胺连接的双卡宾配体的cnc-pincer稀土金属酰胺配合物: 合成，表征和催化活性
PREAI
分享收藏Circulating microRNAs as stable blood-based markers for cancer detection循环microrna作为稳定的血液标志物用于癌症检测
OAAI
OAAI分享收藏 没有更多内容
没有更多内容