Framing Algorithmic Recourse for Anomaly Detection

TL;DR

This paper introduces CARAT, a novel transformer-based method for generating counterfactual explanations for anomaly detection in tabular data with discrete features, enhancing interpretability and robustness.

Contribution

CARAT is the first approach to provide scalable, model-agnostic counterfactual explanations for anomalies in discrete tabular data, using a transformer encoder-decoder architecture.

Findings

CARAT effectively identifies features with low likelihood in anomalies.

Generated counterfactuals are semantically coherent and contextually relevant.

Experiments demonstrate CARAT's scalability and robustness across datasets.

Abstract

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.