Score-based Integrated Gradient for Root Cause Explanations of Outliers
This work addresses a fundamental issue in causal inference and anomaly detection for applications like cloud services and supply chains, offering a scalable and uncertainty-aware solution that improves upon existing methods.
The paper tackles the problem of identifying root causes of outliers in causal inference and anomaly detection by introducing SIREN, a method that uses score functions and integrated gradients for attribution, achieving superior performance in accuracy and efficiency on synthetic and real-world datasets.
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.