Score-based Integrated Gradient for Root Cause Explanations of Outliers

TL;DR

SIREN is a scalable, score-based method for root cause analysis of outliers that leverages integrated gradients and satisfies key axioms, outperforming existing approaches in accuracy and efficiency.

Contribution

We introduce SIREN, a novel approach that uses score functions and integrated gradients for root cause attribution, handling high-dimensional and nonlinear data effectively.

Findings

SIREN outperforms state-of-the-art methods in accuracy.

SIREN is more computationally efficient.

SIREN effectively handles high-dimensional, nonlinear, and heteroscedastic models.

Abstract

Identifying the root causes of outliers is a fundamental problem in causal inference and anomaly detection. Traditional approaches based on heuristics or counterfactual reasoning often struggle under uncertainty and high-dimensional dependencies. We introduce SIREN, a novel and scalable method that attributes the root causes of outliers by estimating the score functions of the data likelihood. Attribution is computed via integrated gradients that accumulate score contributions along paths from the outlier toward the normal data distribution. Our method satisfies three of the four classic Shapley value axioms - dummy, efficiency, and linearity - as well as an asymmetry axiom derived from the underlying causal structure. Unlike prior work, SIREN operates directly on the score function, enabling tractable and uncertainty-aware root cause attribution in nonlinear, high-dimensional, and heteroscedastic causal models. Extensive experiments on synthetic random graphs and real-world cloud service and supply chain datasets show that SIREN outperforms state-of-the-art baselines in both attribution accuracy and computational efficiency.