arXiv:1810.02678
Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections
원문 초록
We introduce a method, KL-LIME, for explaining predictions of Bayesian predictive models by projecting the information in the predictive distribution locally to a simpler, interpretable explanation model. The proposed approach combines the recent Local Interpretable Model-agnostic Explanations (LIME) method with ideas from Bayesian projection predictive variable selection methods. The information theoretic basis helps in navigating the trade-off between explanation fidelity and complexity. We demonstrate the method in explaining MNIST digit classifications made by a Bayesian deep convolutional neural network.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Handling bounded response in high dimensions: a Horseshoe prior Bayesian Beta regression approach
Stability Selection via Variable Decorrelation
High Dimensional Bayesian Optimization using Lasso Variable Selection
Causal Feature Learning in the Social Sciences
Bayesian Cox model with graph-structured variable selection priors for multi-omics biomarker identification
AirCast: Improving Air Pollution Forecasting Through Multi-Variable Data Alignment
토론
이 논문과 연결된 포럼 글이 아직 없습니다.