CASTLE: Cluster-aided space transformation for local explanations

作者：

Highlights：

• CASTLE aims to combine local and global features to explain any AI system predictions.

• Model’s global knowledge, as rules, supports the local explanation generation process.

• CASTLE estimates how clusters’ representative points in uence predictions.

• It supports any explanation type (e.g. rule-based, feature importance, counterfactual).

摘要

•CASTLE aims to combine local and global features to explain any AI system predictions.•Model’s global knowledge, as rules, supports the local explanation generation process.•CASTLE estimates how clusters’ representative points in uence predictions.•It supports any explanation type (e.g. rule-based, feature importance, counterfactual).

论文关键词：eXplainable Artificial Intelligence,Clustering,Artificial Intelligence,Machine learning

论文评审过程：Received 11 August 2020, Revised 2 March 2021, Accepted 12 April 2021, Available online 20 April 2021, Version of Record 5 May 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115045