Framing Algorithmic Recourse for Anomaly Detection

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.

arXiv commentACM SigKDD 2022, Research Track

References in corpus (13)

• Learning Important Features Through Propagating Activation Differences
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Actionable Recourse in Linear Classification
• InterpretML: A Unified Framework for Machine Learning Interpretability
• CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• Entity Embedding-based Anomaly Detection for Heterogeneous Categorical Events
• Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
• Interpretable Anomaly Detection with DIFFI: Depth-based Isolation Forest Feature Importance