A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov-Smirnov bounds
From MaRDI portal
Publication:2057739
Abstract: A new robust algorithm based of the explanation method SurvLIME called SurvLIME-KS is proposed for explaining machine learning survival models. The algorithm is developed to ensure robustness to cases of a small amount of training data or outliers of survival data. The first idea behind SurvLIME-KS is to apply the Cox proportional hazards model to approximate the black-box survival model at the local area around a test example due to the linear relationship of covariates in the model. The second idea is to incorporate the well-known Kolmogorov-Smirnov bounds for constructing sets of predicted cumulative hazard functions. As a result, the robust maximin strategy is used, which aims to minimize the average distance between cumulative hazard functions of the explained black-box model and of the approximating Cox model, and to maximize the distance over all cumulative hazard functions in the interval produced by the Kolmogorov-Smirnov bounds. The maximin optimization problem is reduced to the quadratic program. Various numerical experiments with synthetic and real datasets demonstrate the SurvLIME-KS efficiency.
Recommendations
Cites work
- A probabilistic approach to the geometry of the \(\ell^n_p\)-ball
- Adaptive Lasso for Cox's proportional hazards model
- An efficient explanation of individual classifications using game theory
- Analysis of survival data with group lasso
- Building classification trees using the total uncertainty criterion
- Classification with decision trees from a nonparametric predictive inference perspective
- Classification with support vector machines and Kolmogorov-Smirnov bounds
- Combining imprecise probability masses with maximal coherent subsets: application to ensemble classification
- Definitions, methods, and applications in interpretable machine learning
- scientific article; zbMATH DE number 48344 (Why is no real title available?)
- scientific article; zbMATH DE number 686769 (Why is no real title available?)
- scientific article; zbMATH DE number 1005417 (Why is no real title available?)
- scientific article; zbMATH DE number 3795247 (Why is no real title available?)
- scientific article; zbMATH DE number 845703 (Why is no real title available?)
- scientific article; zbMATH DE number 5209873 (Why is no real title available?)
- scientific article; zbMATH DE number 3222455 (Why is no real title available?)
- scientific article; zbMATH DE number 3385132 (Why is no real title available?)
- Learning reliable classifiers from small or incomplete data sets: the naive credal classifier 2
- Learning with imprecise probabilities as model selection and averaging
- Nonparametric predictive inference with right-censored data
- On decompositional algorithms for uniform sampling from n-spheres and n-balls
- Random forests
- Reliable survival analysis based on the Dirichlet process
- Robustness and regularization of support vector machines
- The imprecise logit-normal model and its application to estimating hazard functions
- Uses and computation of imprecise probabilities from statistical data and expert arguments
Cited in
(3)
This page was built for publication: A robust algorithm for explaining unreliable machine learning survival models using the Kolmogorov-Smirnov bounds
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057739)
