The Shapley value concept from cooperative game theory has become a popular technique for interpreting ML models, but efficiently estimating these values remains challenging, particularly in the model-agnostic setting. Here, we revisit the idea of estimating Shapley values via linear regression to understand and improve upon this approach. By analyzing the original KernelSHAP alongside a newly proposed unbiased version, we develop techniques to detect its convergence and calculate uncertainty estimates. We also find that the original version incurs a negligible increase in bias in exchange for significantly lower variance, and we propose a variance reduction technique that further accelerates the convergence of both estimators. Finally, we develop a version of KernelSHAP for stochastic cooperative games that yields fast new estimators for two global explanation methods.
Approximate Shapley value estimation using sampling without replacement and variance estimation via the new Symmetric bootstrap and the Doubled half bootstrap
J.P. Morgan AI Research（摩根大通人工智能研究院）；King’s College London（伦敦国王学院）
Feature importance techniques have enjoyed widespread attention in the explainable AI literature as a means of determining how trained machine learning models make their predictions. We consider Shapley value based approaches to feature importance, applied in the context of time series data. We present closed form solutions for the SHAP values of a number of time series models, including VARMAX. We also show how KernelSHAP can be applied to time series tasks, and how the feature importances that come from this technique can be combined to perform "event detection". Finally, we explore the use …
Distributional data Shapley value (DShapley) has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning. DShapley develops the foundational game theory concept of Shapley values into a statistical framework and can be applied to identify data points that are useful (or harmful) to a learning algorithm. Estimating DShapley is computationally expensive, however, and this can be a major challenge to using it in practice. Moreover, there has been little mathematical analyses of how this value depends on data characteristics. In this pa…
Norwegian University of Science and Technology (NTNU)（挪威科技大学 (NTNU)）
We investigate the effect of including domain knowledge about a robotic system's causal relations when generating explanations. To this end, we compare two methods from explainable artificial intelligence, the popular KernelSHAP and the recent causal SHAP, on a deep neural network trained using deep reinforcement learning on the task of controlling a lever using a robotic manipulator. A primary disadvantage of KernelSHAP is that its explanations represent only the features' direct effects on a model's output, not considering the indirect effects a feature can have on the output by affecting ot…
We introduce a new Shapley value approach for global sensitivity analysis and machine learning explainability. The method is based on the first-order partial derivatives of the underlying function. The computational complexity of the method is linear in dimension (number of features), as opposed to the exponential complexity of other Shapley value approaches in the literature. Examples from global sensitivity analysis and machine learning are used to compare the method numerically with activity scores, SHAP, and KernelSHAP.
Tractable Shapley Values and Interactions via Tensor Networks
DIRO & Mila Université de Montréal（DIRO与Mila蒙特利尔大学）；RIKEN AIP（日本理化学研究所AIP）；DIRO & Mila, CIFAR AI Chair（DIRO与Mila，CIFAR人工智能主席）；Université de Montréal（蒙特利尔大学）
Comparative Evaluation of Explainable Machine Learning Versus Linear Regression for Predicting County-Level Lung Cancer Mortality Rate in the United States
University of Tennessee Graduate School（田纳西大学研究生院）
Shapley values are great analytical tools in game theory to measure the importance of a player in a game. Due to their axiomatic and desirable properties such as efficiency, they have become popular for feature importance analysis in data science and machine learning. However, the time complexity to compute Shapley values based on the original formula is exponential, and as the number of features increases, this becomes infeasible. Castro et al. [1] developed a sampling algorithm, to estimate Shapley values. In this work, we propose a new sampling method based on a multilinear extension techni…
Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond
School of Computer Science, University of Waterloo, Canada（滑铁卢大学计算机科学学院）；Department of Computer Science, National University of Singapore, Republic of Singapore（新加坡国立大学计算机科学系）；Vector Institute, Canada（加拿大向量研究所）
Örebro University, School of Science and Technology（奥雷布罗大学，科学与技术学院）；KTH Royal Institute of Technology, School of Electrical Engineering and Computer Science（皇家理工学院，电气工程与计算机科学学院）
Random forests have been widely used for their ability to provide so-called importance measures, which give insight at a global (per dataset) level on the relevance of input variables to predict a certain output. On the other hand, methods based on Shapley values have been introduced to refine the analysis of feature relevance in tree-based models to a local (per instance) level. In this context, we first show that the global Mean Decrease of Impurity (MDI) variable importance scores correspond to Shapley values under some conditions. Then, we derive a local MDI importance measure of variable …
Department of Statistics, LMU Munich（LMU慕尼黑统计系）；Department of Electrical Engineering and Computer Science, UC Berkeley（伯克利电子工程与计算机科学系）；Mathematical Sciences Department, Claremont McKenna College（克莱门茨麦肯纳学院数学科学系）
Chunked Data Shapley: A Scalable Dataset Quality Assessment for Machine Learning
Knowledge Systems Lab School of ECE, National Technical University of Athens Athens Greece；Knowledge Systems Lab School of ECE, National Technical University of Athens
A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty
Leibniz Institute for Prevention Research and Epidemiology – BIPS（莱布尼茨预防研究与流行病学研究所——BIPS）；University of Bremen（不来梅大学）；Simula Research Laboratory（西穆拉研究实验室）；Telenor Research & Innovation（挪威电信研究与创新部）；Norwegian Computing Center（挪威计算中心）
Model interpretability is one of the most intriguing problems in most of the Machine Learning models, particularly for those that are mathematically sophisticated. Computing Shapley Values are arguably the best approach so far to find the importance of each feature in a model, at the row level. In other words, Shapley values represent the importance of a feature for a particular row, especially for Classification or Regression problems. One of the biggest limitations of Shapley vales is that, Shapley value calculations assume all the features are uncorrelated (independent of each other), this …
Shapley-Based Data Valuation with Mutual Information: A Key to Modified K-Nearest Neighbors
1 Department of Electrical；Computer Engineering, Aarhus University, Denmark 2 Department of Electrical；Computer Engineering, Universitat Polit\`ecnica de Val\`encia, Spain 3 Department of Electrical；Computer Engineering, University of Tehran, Iran
QuadraSHAP: $ε$-Exact Shapley Values for Product Games in Logarithmic Parallel Time
AI Technology for Life, Information and Computing Sciences, Utrecht University, The Netherlands（荷兰乌得勒支大学人工智能技术与信息计算科学系）；Biomolecular Mass Spectrometry and Proteomics, Pharmaceutical Sciences, Utrecht University, The Netherlands（荷兰乌得勒支大学生物分子质谱与蛋白质组学，药学科学系）；Rational Intelligence Lab, CISPA Helmholtz Center for Information Security, Germany（德国CISPA海德堡信息安全中心理性智能实验室）；Epistemic Intelligence & Computation Lab, College of Computing & Data Science, Nanyang Technological University, Singapore（新加坡南洋理工大学认知智能与计算实验室）
University of Applied Sciences and Arts Dortmund（多特蒙德应用科学与艺术大学）；University Hospital Essen（埃森大学医院）
Purpose: Hard-to-interpret Black-box Machine Learning (ML) were often used for early Alzheimer's Disease (AD) detection. Methods: To interpret eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM) black-box models a workflow based on Shapley values was developed. All models were trained on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset and evaluated for an independent ADNI test set, as well as the external Australian Imaging and Lifestyle flagship study of Ageing (AIBL), and Open Access Series of Imaging Studies (OASIS) datasets. Shapley valu…
KAIST（韩国科学技术院）；University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）
The transfer fees of sports players have become astronomical. This is because bringing players of great future value to the club is essential for their survival. We present a case study on the key factors affecting the world's top soccer players' transfer fees based on the FIFA data analysis. To predict each player's market value, we propose an improved LightGBM model by optimizing its hyperparameter using a Tree-structured Parzen Estimator (TPE) algorithm. We identify prominent features by the SHapley Additive exPlanations (SHAP) algorithm. The proposed method has been compared against the ba…
One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently
School of Computing（计算机学院）；National University of Singapore（新加坡国立大学）；School of Computer Science（计算机科学学院）；University of Waterloo（滑铁卢大学）；Vector Institute（向量研究院）
Medical artificial intelligence toolbox (MAIT): an explainable machine learning framework for binary classification, survival modelling, and regression analyses
Rigshospitalet, Copenhagen University Hospital（哥本哈根大学医院丽格医院）；Centre of Excellence for Health, Immunity and Infections (CHIP)（健康、免疫与感染卓越中心）
CoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property Prediction
School of Mathematics, Jilin University（吉林大学数学学院）；AI for Science and Engineering Center, Shenzhen Loop Area Institute（深圳循环区研究院科学与工程人工智能中心）；BGP Inc., China National Petroleum Corporation（中国石油天然气集团公司东方地球物理公司）；National Engineering Research Center of Oil & Gas Exploration Computer Software（油气勘探计算机软件国家工程研究中心）
PBLH Estimation from Satellite Radiances via a Dual-Encoder Transformer
Politecnico di Torino（都灵理工大学）；Fondazione LINKS（LINKS基金会）；Institute of Integrated Methodologies for Earth Observation, National Research Council (IMIOT/CNR)（地球观测综合方法研究所，国家研究委员会（IMIOT/CNR））；University of Calabria（卡拉布里亚大学）
