Explaining anomalies detected by autoencoders using Shapley Additive Explanations

作者：

Highlights：

• Explaining anomalies identified by autoencoder using shapley values.

• Explain features with high reconstruction error.

• Evaluated correctness and robustness of explanations.

• Explanations can assist in reducing anomaly score.

• Conducted experts evaluation to examine the explanation method.

摘要

•Explaining anomalies identified by autoencoder using shapley values.•Explain features with high reconstruction error.•Evaluated correctness and robustness of explanations.•Explanations can assist in reducing anomaly score.•Conducted experts evaluation to examine the explanation method.

论文关键词：Explainable black-box models,XAI,Autoencoder,Shapley values,SHAP,Anomaly detection

论文评审过程：Received 8 December 2020, Revised 5 August 2021, Accepted 5 August 2021, Available online 11 August 2021, Version of Record 18 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115736