Rule extraction in unsupervised anomaly detection for model explainability: Application to OneClass SVM
作者：
Highlights：
• Rule extraction for unsupervised outlier detection models using OCSVM.
• Design and evaluate alternatives over rule extraction algorithms.
• XAI metric evaluation: comprehensibility, representativeness, stability and diversity.
• Quantify quality of the explanations with XAI metrics for P@1 rules.
• Measure the kernel influence in the number of rules generated.
摘要
•Rule extraction for unsupervised outlier detection models using OCSVM.•Design and evaluate alternatives over rule extraction algorithms.•XAI metric evaluation: comprehensibility, representativeness, stability and diversity.•Quantify quality of the explanations with XAI metrics for P@1 rules.•Measure the kernel influence in the number of rules generated.
论文关键词：XAI,OneClass SVM,Unsupervised learning,Rule extraction,Anomaly detection,Metrics
论文评审过程：Received 17 June 2020, Revised 13 October 2021, Accepted 13 October 2021, Available online 23 October 2021, Version of Record 2 November 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.116100
