Beyond Single-Feature Importance with ICECREAM
It addresses explainability and root cause analysis for machine learning and cloud computing, offering a novel approach beyond single-feature importance.
The paper tackles the problem of identifying sets of features responsible for specific model outputs or system failures, proposing ICECREAM to measure coalition influence and outperforming state-of-the-art methods in experiments.
Which set of features was responsible for a certain output of a machine learning model? Which components caused the failure of a cloud computing application? These are just two examples of questions we are addressing in this work by Identifying Coalition-based Explanations for Common and Rare Events in Any Model (ICECREAM). Specifically, we propose an information-theoretic quantitative measure for the influence of a coalition of variables on the distribution of a target variable. This allows us to identify which set of factors is essential to obtain a certain outcome, as opposed to well-established explainability and causal contribution analysis methods which can assign contributions only to individual factors and rank them by their importance. In experiments with synthetic and real-world data, we show that ICECREAM outperforms state-of-the-art methods for explainability and root cause analysis, and achieves impressive accuracy in both tasks.