.png){kind=icon}
返回
Learning From Imbalanced Data Using Triplet Adversarial Samples
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3262604.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The imbalance of classes in real-world datasets poses a major challenge in machine learning and classification, and traditional synthetic data generation methods often fail to address this problem effectively. A major limitation of these methods is that they tend to separate the process of generating synthetic samples from the training process, resulting in synthetic data that lack the necessary informative characteristics for proper model training. We present a new synthetic data generation method that addresses this issue by combining adversarial sample generation with a triplet loss method. This approach focuses on increasing the diversity in the minority class while preserving the integrity of the decision boundary. Furthermore, we show that reducing triplet loss is equivalent to maximizing the area under the receiver operating characteristic curve under specific conditions, providing a theoretical basis for the effectiveness of our method. In addition, we present a model training approach to further improve the generalization of the model to small classes by providing a diverse set of synthetic samples optimized using our proposed loss function. We evaluated our method on several imbalanced benchmark tasks and compared it to state-of-the-art techniques, demonstrating that our method can deliver even better performance, making it an effective solution to the class imbalance problem.
Keyword:
Data generation
Synthetic data
Data models
Optimization
Neural networks
Deep learning
Adaptation models
Class imbalance
triplet loss
adversarial samples
synthetic data generation
multiple classes
area under ROC
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
分享收藏A systematic study of the class imbalance problem in convolutional neural networks卷积神经网络中类不平衡问题的系统研究.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏THE MEANING AND USE OF THE AREA UNDER A RECEIVER OPERATING CHARACTERISTIC (ROC) CURVE受试者工作特征 (ROC) 曲线下面积的含义和用途RADIOLOGY
RADIOLOGYIF15.2
PREAI
分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容