Research map / Probabilistic and scientific modeling / Molecules and proteins
Functional Decomposition and Shapley Interactions for Interpreting Survival Models
Sophie Hanna Langbein, Hubert Baniecki, Fabian Fumagalli, Niklas Koenen, Marvin N. Wright, Julia Herbinger
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use a flexible GBSA model instead of CoxPH without pre-specified interactions | survival model on simulated data with interactions · simulated scenario (8) | C-index: 0.66 -> 0.70 | Improved |
| use GBSA instead of CoxPH without pre-specified interactions | survival model on simulated data with interactions · simulated scenario (8) | IBS: 0.16 -> 0.15 | Improved |
| move from first-order Shapley values to second-order SurvSHAP-IQ individual effects (ablation) | GBSA model for uveal melanoma · uveal melanoma validation set | in-group variance of attributions | Improved |
| use the regression-based (kernel) approximator rather than sampling-based ones when the budget is large enough (ablation) | SurvSHAP-IQ approximation · Bergamaschi and three other 10-16 feature survival tasks | approximation error (MAE) | Improved |
| use the regression-based approximator at a very small sampling budget (26) (ablation) | SurvSHAP-IQ approximation · Bergamaschi task, order 2 | approximation error (MAE) | Hurt |
| explain predictions on hazard or survival scale instead of log-hazard scale (ablation) | SurvFD decomposition of a linear CoxPH risk score · simulated scenario (1) | interaction attributions | Hurt |
Closest papers by meaning
- Gradient-based Explanations for Deep Learning Survival Models (ICML 2025 · similarity 0.88)
- SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference (NeurIPS 2026 · similarity 0.86)
- Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data (NeurIPS 2025 · similarity 0.85)
- Doubly Robust Conformalized Survival Analysis with Right-Censored Data (ICML 2025 · similarity 0.85)
- Deep Copula-Based Survival Analysis for Dependent Censoring with Identifiability Guarantees (AAAI 2024 · similarity 0.84)
- CA-MLIF: Cross-Attention and Multimodal Low-Rank Interaction Fusion Framework for Tumor Prognostic Prediction (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
