A Characteristic Function for Shapley-Value-Based Attribution of Anomaly Scores
This work addresses the need for interpretability in anomaly detection, particularly for semi-supervised methods, but is incremental as it builds on existing Shapley value techniques.
The paper tackled the problem of interpreting anomaly detection results by attributing anomaly scores to input features, proposing a characteristic function for Shapley-value-based attribution that approximates feature absence by locally minimizing scores, with results indicating potential utility across multiple datasets and methods.
In anomaly detection, the degree of irregularity is often summarized as a real-valued anomaly score. We address the problem of attributing such anomaly scores to input features for interpreting the results of anomaly detection. We particularly investigate the use of the Shapley value for attributing anomaly scores of semi-supervised detection methods. We propose a characteristic function specifically designed for attributing anomaly scores. The idea is to approximate the absence of some features by locally minimizing the anomaly score with regard to the to-be-absent features. We examine the applicability of the proposed characteristic function and other general approaches for interpreting anomaly scores on multiple datasets and multiple anomaly detection methods. The results indicate the potential utility of the attribution methods including the proposed one.