Results 11 to 20 of about 29,456 (261)
Corr-SHAP: Correlation-Aware Sampling for Faithful SHAP Value Estimation
Acta Informatica PragensiaBackground: SHapley Additive exPlanations (SHAP) methods are widely used to interpret machine learning models, yet most implementations assume feature independence.
Ridha El Hamdi +3 more
doaj +2 more sources
Effective Pruning for Top-k Feature Search on the Basis of SHAP Values
IEEE AccessWith the ever-increasing influence of machine learning models, it has become necessary to explain their predictions. The SHAP framework provides a solution to this problem by assigning a score to each feature of a model such that it reflects the feature ...
Lisa Chabrier +3 more
doaj +6 more sources
mSHAP: SHAP Values for Two-Part Models [PDF]
Risks, 2021 Two-part models are important to and used throughout insurance and actuarial science. Since insurance is required for registering a car, obtaining a mortgage, and participating in certain businesses, it is especially important that the models that price insurance policies are fair and non-discriminatory.
Spencer Matthews, Brian Hartman
openaire +4 more sources
RKHS-SHAP: Shapley Values for Kernel Methods
Advances in Neural Information Processing Systems 35, 2022 Feature attribution for kernel methods is often heuristic and not individualised for each prediction. To address this, we turn to the concept of Shapley values~(SV), a coalition game theoretical framework that has previously been applied to different machine learning model interpretation tasks, such as linear models, tree ensembles and deep networks ...
Siu Lun Chau +3 more
openaire +4 more sources
REFRESH: Responsible and Efficient Feature Reselection guided by SHAP values
Proceedings of the 2023 AAAI/ACM Conference on AI, Ethics, and Society, 2023 Feature selection is a crucial step in building machine learning models. This process is often achieved with accuracy as an objective, and can be cumbersome and computationally expensive for large-scale datasets. Several additional model performance characteristics such as fairness and robustness are of importance for model development.
Shubham Sharma +5 more
openaire +4 more sources
Unfooling SHAP and SAGE: Knockoff Imputation for Shapley Values
, 2023 AbstractShapley values have achieved great popularity in explainable artificial intelligence. However, with standard sampling methods, resulting feature attributions are susceptible to adversarial attacks. This originates from target function evaluations at extrapolated data points, which are easily detectable and hence, enable models to behave ...
Kristin Blesch +2 more
openaire +1 more source
Arthritis Research & Therapy, 2022 Background The purpose of this study was to stratify patients with rheumatoid arthritis (RA) according to the trend of disease activity by trajectory-based clustering and to identify contributing factors for treatment response to biologic and targeted ...
Bon San Koo +7 more
doaj +1 more source
SHAP-XRT: The Shapley Value Meets Conditional Independence Testing
Trans. Mach. Learn. Res., 2022 The complex nature of artificial neural networks raises concerns on their reliability, trustworthiness, and fairness in real-world scenarios. The Shapley value -- a solution concept from game theory -- is one of the most popular explanation methods for machine learning models.
Jacopo Teneggi +3 more
openaire +3 more sources
Frontiers in Energy Research, 2023 Load forecasting is an important prerequisite and foundation for ensuring the rational planning and safe operation of integrated energy systems. In view of the interactive coupling problem among multivariate loads, this paper constructs a TCN-GAT ...
Qianyun Zheng +5 more
doaj +1 more source
A Physically Interpretable Rice Field Extraction Model for PolSAR Imagery
Remote Sensing, 2023 Reliable and timely rice distribution information is of great value for real-time, quantitative, and localized control of rice production information.
Ji Ge +6 more
doaj +1 more source