Functional Decomposition and Shapley Interactions for Interpreting Survival Models
Not on the map. Why?
Abstract (arXiv)
Hazard and survival functions are natural, interpretable targets in time-to-event prediction, but their inherent non-additivity fundamentally limits standard additive explanation methods. We introduce Survival Functional Decomposition (SurvFD), a principled approach for analyzing feature interactions in machine learning survival models. By decomposing higher-order effects into time-dependent and time-independent components, SurvFD offers a previously unrecognized perspective on survival explanations, explicitly characterizing when and why additive explanations fail. Building on this theoretical decomposition, we propose SurvSHAP-IQ, which extends Shapley interactions to time-indexed functions, providing a practical estimator for higher-order, time-dependent interactions. Together, SurvFD and SurvSHAP-IQ establish an interaction- and time-aware interpretability approach for survival modeling, with broad applicability across time-to-event prediction tasks.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 23 of its 68 references that are in the map. First posted on arXiv 18 Feb 2026.
Builds on
23 of 68 references.
References · 23
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2018Attention-based Deep Multiple Instance Learningcited by 1,077
- 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
- 2019Time-to-Event Prediction with Neural Networks and Cox Regressioncited by 173
- 2019The Shapley Taylor Interaction Indexcited by 143
- 2020True to the Model or True to the Data?cited by 123
- 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
- 2023Deep Learning for Survival Analysis: A Reviewcited by 75
- 2022Faith-Shap: The Faithful Shapley Interaction Indexcited by 68
- 2022From Shapley Values to Generalized Additive Models and backcited by 59
- 2023SHAP-IQ: Unified Approximation of any-order Shapley Interactionscited by 50
- 2020Survival regression with accelerated failure time model in XGBoostcited by 37
11 more
- 2020SurvLIME: A method for explaining machine learning survival modelscited by 34
- 2022SurvSHAP(t): Time-dependent explanations of machine learning survival modelscited by 24
- 2024KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactionscited by 22
- 2021Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Featurescited by 19
- 2025Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Valuescited by 19
- 2024SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratificationcited by 16
- 2022SurvSet: An open-source time-to-event dataset repositorycited by 15
- 2024Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theorycited by 10
- 2023Interpretable machine learning for time-to-event prediction in medicine and healthcarecited by 7
- 2025Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactionscited by 6
- 2025Gradient-based Explanations for Deep Learning Survival Modelscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.