Results 11 to 20 of about 44,463 (307)
On the Tractability of SHAP Explanations
Journal of Artificial Intelligence Research, 2021 SHAP explanations are a popular feature-attribution mechanism for explainable AI. They use game-theoretic notions to measure the influence of individual features on the prediction of a machine learning model. Despite a lot of recent interest from both academia and industry, it is not known whether SHAP explanations of common machine learning ...
Guy Van den Broeck +3 more
openaire +3 more sources
Conditional Expectation Network for SHAP
SSRN Electronic Journal, 2023 A very popular model-agnostic technique for explaining predictive models is the SHapley Additive exPlanation (SHAP). The two most popular versions of SHAP are a conditional expectation version and an unconditional expectation version (the latter is also known as interventional SHAP).
Ronald Richman, Mario V. Wüthrich
openaire +3 more sources
Proceedings of the AAAI Conference on Artificial IntelligenceSHAP scores represent the proposed use of the well-known Shapley values in eXplainable Artificial Intelligence (XAI). Recent work has shown that the exact computation of SHAP scores can produce unsatisfactory results. Concretely, for some ML models, SHAP scores will mislead with respect to relative feature influence.
Olivier Létoffé +2 more
core +4 more sources
Journal of Hydroinformatics, 2023 In contrast to the traditional black box machine learning model, the white box model can achieve higher prediction accuracy and accurately evaluate and explain the prediction results.
Shanshan Li *, Guodong Li
exaly +3 more sources
Fooling SHAP with Output Shuffling Attacks
CoRRExplainable AI~(XAI) methods such as SHAP can help discover feature attributions in black-box models. If the method reveals a significant attribution from a ``protected feature'' (e.g., gender, race) on the model output, the model is considered unfair. However, adversarial attacks can subvert the detection of XAI methods.
Jun Yuan, Aritra Dasgupta 0001
openaire +3 more sources
Research on a short-term photovoltaic power prediction method based on CatBoost
Zhejiang dianli, 2023 The intermittent and fluctuating generation power of PV power plants has an increasingly prominent impact on the safe， stable， and economical operation of power grids.
CHEN Haihong +3 more
doaj +1 more source
Reviews in Cardiovascular Medicine, 2023 Background: Using deep learning for disease outcome prediction is an approach that has made large advances in recent years. Notwithstanding its excellent performance, clinicians are also interested in learning how input affects prediction.
Chien-Yu Chi +9 more
doaj +1 more source
International Journal of Strategic Property Management, 2021 This study aims to bridge the gap between two perspectives of explainability−machine learning and engineering, and economics and standard econometrics−by applying three marginal measurements.
Dong-sup Kim, Seungwoo Shin
doaj +1 more source
Algorithms, 2022 The ensemble-based modifications of the well-known SHapley Additive exPlanations (SHAP) method for the local explanation of a black-box model are proposed. The modifications aim to simplify the SHAP which is computationally expensive when there is a large number of features.
Lev V. Utkin, Andrei V. Konstantinov
openaire +3 more sources
智能科学与技术学报, 2023 企业影响力的高低不仅关系到其行业竞争力，也影响着其社会声誉和未来发展，然而对企业影响力的评价一直没有统一的标准。GitHub是一个代表性的软件开发代码存储库开源平台，现有研究通常使用企业在GitHub发布的项目得到的star总数衡量其影响力高低，但是这种方式难以衡量小微企业和新生企业的潜力。通过引入科学家的影响力衡量指标h指数，以GitHub为信息源进行企业网络建模，同时基于该网络提取特征构建分类器，对企业未来的影响力水平进行预测。在此基础上应用SHAP模型解释技术，判别决定企业影响力的重要特征 ...
王明宇, 宫庆媛, 瞿晶晶, 王新
doaj +1 more source