Counterfactual explanation of machine learning survival models
From MaRDI portal
Abstract: A method for counterfactual explanation of machine learning survival models is proposed. One of the difficulties of solving the counterfactual explanation problem is that the classes of examples are implicitly defined through outcomes of a machine learning survival model in the form of survival functions. A condition that establishes the difference between survival functions of the original example and the counterfactual is introduced. This condition is based on using a distance between mean times to event. It is shown that the counterfactual explanation problem can be reduced to a standard convex optimization problem with linear constraints when the explained black-box model is the Cox model. For other black-box models, it is proposed to apply the well-known Particle Swarm Optimization algorithm. A lot of numerical experiments with real and synthetic data demonstrate the proposed method.
Recommendations
- A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov-Smirnov bounds
- A Symbolic Approach for Counterfactual Explanations
- A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C
- An ASP-based approach to counterfactual explanations for classification
- Assessing heuristic machine learning explanations with model counting
Cites work
- scientific article; zbMATH DE number 5209873 (Why is no real title available?)
- scientific article; zbMATH DE number 3385132 (Why is no real title available?)
- A comprehensive survey on particle swarm optimization algorithm and its applications
- A mixed-discrete particle swarm optimization algorithm with explicit diversity-preservation
- A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov-Smirnov bounds
- Adaptive Lasso for Cox's proportional hazards model
- An efficient explanation of individual classifications using game theory
- Analysis of survival data with group lasso
- Assessing Influence in Regression Analysis with Censored Data
- Random forests
- Recursive partitioning for heterogeneous causal effects
Cited in
(11)- Note on the bi-risk discrete time risk model with income rate two
- Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
- A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C
- Assessing heuristic machine learning explanations with model counting
- MCCE: Monte Carlo sampling of valid and realistic counterfactual explanations for tabular data
- Model-agnostic explanations for survival prediction models
- Enhancing the interpretability of nonlinear proportional hazard models introducing ghost variables
- Disagreement amongst counterfactual explanations: how transparency can be misleading
- A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov-Smirnov bounds
- Interpretable machine learning for survival analysis
- A Symbolic Approach for Counterfactual Explanations
This page was built for publication: Counterfactual explanation of machine learning survival models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5862149)
