Framing Algorithmic Recourse for Anomaly Detection
Framing Algorithmic Recourse for Anomaly Detection
复制标题
DOI：
10.1145/3534678.3539344
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Debanjan Datta;F. Chen;Naren Ramakrishnan
中科院分区：
文献类型：
--
作者：
Debanjan Datta;F. Chen;Naren Ramakrishnan
算法追索权的问题已经被探索用于监督机器学习模型，以从决策支持系统提供更可解释、透明和鲁棒的结果。一个未探索的领域是异常检测的算法资源，特别是对于只有离散特征值的表格数据。这里的问题是提出一组被底层异常检测模型视为正常的反事实，以便应用程序可以利用此信息进行解释或推荐对策。我们提出了一种方法-上下文保持的表格数据中的异常（CARAT），这是有效的，可扩展的，和不可知的底层异常检测模型。CARAT使用基于Transformer的编码器-解码器模型，通过查找具有低可能性的特征来解释异常。随后，通过修改突出显示的特征，使用异常实例中特征的整体上下文来生成语义上连贯的反事实。大量的实验有助于证明CARAT的功效。
The problem of algorithmic recourse has been explored for supervised machine learning models, to provide more interpretable, transparent and robust outcomes from decision support systems. An unexplored area is that of algorithmic recourse for anomaly detection, specifically for tabular data with only discrete feature values. Here the problem is to present a set of counterfactuals that are deemed normal by the underlying anomaly detection model so that applications can utilize this information for explanation purposes or to recommend countermeasures. We present an approach-Context preserving Algorithmic Recourse for Anomalies in Tabular data(CARAT), that is effective, scalable, and agnostic to the underlying anomaly detection model. CARAT uses a transformer based encoder-decoder model to explain an anomaly by finding features with low likelihood. Subsequently semantically coherent counterfactuals are generated by modifying the highlighted features, using the overall context of features in the anomalous instance(s). Extensive experiments help demonstrate the efficacy of CARAT.