.png){kind=icon}
返回
Corruption-based anomaly detection and interpretation in tabular data
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.111149.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent advances in self-supervised learning (SSL) have proven crucial in effectively learning representations of unstructured data, encompassing text, images, and audio. Although the applications of these advances in anomaly detection have been explored extensively, applying SSL to tabular data presents challenges because of the absence of prior information on data structure. In response, we propose a framework for anomaly detection in tabular datasets using variable corruption. Through selective variable corruption and assignment of new labels based on the degree of corruption, our framework can effectively distinguish between normal and abnormal data. Furthermore, analyzing the impact of corruption on anomaly scores aids in the identification of important variables. Experimental results obtained from various tabular datasets validate the precision and applicability of the proposed method. The source code can be accessed at https://github.com/mokch/CAIT.
Keyword:
Anomaly detection
Tabular data
Explainable artificial intelligence
Variable corruption
Self-supervised learning
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
MF-Net: Multi-frequency intrusion detection network for Internet traffic data.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Anomaly detection via gating highway connection for retinal fundus images通过门控高速公路连接进行视网膜眼底图像的异常检测PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏LPCL: Localized prominence contrastive learning for self-supervised dense visual pre-trainingLPCL: 用于自监督密集视觉预训练的局部突出对比学习PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning基于深度学习的线性单类SVM的高维大规模异常检测PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏DenMune: Density peak based clustering using mutual nearest neighborsDenMune: 使用相互最近邻的基于密度峰值的聚类PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Towards explaining anomalies: A deep Taylor decomposition of one-class modelsPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容