知识增强的自监督表格数据异常检测方法研究OA北大核心CSTPCD
Self-Supervised Tabular Data Anomaly Detection Method Based on Knowledge Enhancement
传统的监督异常检测方法快速发展,为了减少对标签的依赖,自监督预训练方法得到了广泛的研究,同时研究表明额外的内在语义知识嵌入对于表格学习至关重要.为了挖掘表格数据当中存在的丰富知识信息,提出了一种基于知识增强的自监督表格数据异常检测方法(self-supervised tabular data anomaly detection method based on knowledge enhancement,STKE)并进行了改进.提出的数据处理模块将…查看全部>>
The traditional supervised anomaly detection methods have developed rapidly.In order to reduce the depen-dence on labels,self-supervised pre-training methods are widely studied,and the studies show that additional intrinsic semantic knowledge embedding is crucial for table learning.In order to mine the rich knowledge information in tabular data,the self-supervised tabular data anomaly detection method based on knowledge enhancement(STKE)is proposed with the …查看全部>>
高小玉;赵晓永;王磊
北京信息科技大学 信息管理学院,北京 100192北京信息科技大学 信息管理学院,北京 100192北京信息科技大学 信息管理学院,北京 100192
计算机与自动化
异常检测自监督知识增强预训练
anomaly detectionself-supervisedknowledge enhancementpre-training
《计算机工程与应用》 2024 (10)
140-147,8
国家重点研发计划(2019YFB1705402)教育部人文社科规划基金项目(20YJAZH129)北京市教育委员会社科计划重点项目(SZ202011232024).
评论