Beyond Single-Feature Importance with ICECREAM
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 19 Jul 2023.
Builds on
27 of 49 references.
References · 27
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
- 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
- 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
- 2019Feature relevance quantification in explainable AI: A causal problemcited by 164
- 2019The Shapley Taylor Interaction Indexcited by 143
- 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
- 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
- 2020Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)cited by 79
15 more
- 2019Causal structure based root cause analysis of outlierscited by 65
- 2022From Shapley Values to Generalized Additive Models and backcited by 59
- 2021Shapley values for feature selection: The good, the bad, and the axiomscited by 54
- 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
- 2022DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal modelscited by 40
- 2020Reviewing the Need for Explainable Artificial Intelligence (xAI)cited by 29
- 2022Backtracking Counterfactualscited by 15
- 2021Directive Explanations for Actionable Explainability in Machine Learning Applicationscited by 14
- 2021A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sourcescited by 14
- 2013Graded Causation and Defaultscited by 13
- 2020Explainable Artificial Intelligence and Machine Learning: A reality rooted perspectivecited by 12
- 2020Quantifying intrinsic causal contributions via structure preserving interventionscited by 12
- 2023Don't be fooled: label leakage in explanation methods and the importance of their quantitative evaluationcited by 11
- 2020Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learningcited by 10
- 2023On the Interventional Kullback-Leibler Divergencecited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 1.
2 papers.