English
Related papers

Related papers: The many Shapley values for model explanation

200 papers

Developing modern machine learning (ML) applications is data-centric, of which one fundamental challenge is to understand the influence of data quality to ML training -- "Which training examples are 'guilty' in making the trained ML model…

Machine Learning · Computer Science 2022-04-28 Bojan Karlaš , David Dao , Matteo Interlandi , Bo Li , Sebastian Schelter , Wentao Wu , Ce Zhang

The proliferation of large models has intensified the need for efficient data valuation methods to quantify the contribution of individual data providers. Traditional approaches, such as game-theory-based Shapley value and…

Artificial Intelligence · Computer Science 2025-09-24 Le Ma , Shirao Yang , Zihao Wang , Yinggui Wang , Lei Wang , Tao Wei , Kejun Zhang

Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic…

Machine Learning · Statistics 2025-06-18 Marouane Il Idrissi , Agathe Fernandes Machado , Arthur Charpentier

Recent studies have examined the computational complexity of computing Shapley additive explanations (also known as SHAP) across various models and distributions, revealing their tractability or intractability in different settings.…

Machine Learning · Computer Science 2025-02-19 Reda Marzouk , Shahaf Bassan , Guy Katz , Colin de la Higuera

Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little consensus on practical deployment. While theoretical differences are well-documented,…

Machine Learning · Computer Science 2026-04-27 Inês Oliveira e Silva , Sérgio Jesus , Iker Perez , Rita P. Ribeiro , Carlos Soares , Hugo Ferreira , Pedro Bizarro

Despite the popularity of Shapley Values in explaining neural text classification models, computing them is prohibitive for large pretrained models due to a large number of model evaluations. In practice, Shapley Values are often estimated…

Computation and Language · Computer Science 2023-06-01 Chenghao Yang , Fan Yin , He He , Kai-Wei Chang , Xiaofei Ma , Bing Xiang

Originally rooted in game theory, the Shapley Value (SV) has recently become an important tool in machine learning research. Perhaps most notably, it is used for feature attribution and data valuation in explainable artificial intelligence.…

Shapley values are widely recognized as a principled method for attributing importance to input features in machine learning. However, the exact computation of Shapley values scales exponentially with the number of features, severely…

Machine Learning · Computer Science 2025-08-21 Majid Mohammadi , Krikamol Muandet , Ilaria Tiddi , Annette Ten Teije , Siu Lun Chau

Current practice in interpretable machine learning often focuses on explaining the final model trained from data, e.g., by using the Shapley additive explanations (SHAP) method. The recently developed Shapley variable importance cloud…

Machine Learning · Computer Science 2022-12-19 Yilin Ning , Mingxuan Liu , Nan Liu

In explainable machine learning, local post-hoc explanation algorithms and inherently interpretable models are often seen as competing approaches. This work offers a partial reconciliation between the two by establishing a correspondence…

Machine Learning · Computer Science 2023-02-24 Sebastian Bordt , Ulrike von Luxburg

SHAP (SHapley Additive exPlanations) values are a widely used method for local feature attribution in interpretable and explainable AI. We propose an efficient two-stage algorithm for computing SHAP values in both black-box setting and…

Machine Learning · Computer Science 2025-10-24 Ali Gorji , Andisheh Amrollahi , Andreas Krause

An important technique to explore a black-box machine learning (ML) model is called SHAP (SHapley Additive exPlanation). SHAP values decompose predictions into contributions of the features in a fair way. We will show that for a boosted…

Machine Learning · Statistics 2022-08-01 Michael Mayer

Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, leading to additional computational cost at inference time. To…

Machine Learning · Computer Science 2025-07-16 Amr Alkhatib , Roman Bresson , Henrik Boström , Michalis Vazirgiannis

Recent work demonstrated the existence of critical flaws in the current use of Shapley values in explainable AI (XAI), i.e. the so-called SHAP scores. These flaws are significant in that the scores provided to a human decision-maker can be…

Artificial Intelligence · Computer Science 2025-02-18 Joao Marques-Silva , Xuanxiang Huang , Olivier Letoffe

Shapley values have been used extensively in machine learning, not only to explain black box machine learning models, but among other tasks, also to conduct model debugging, sensitivity and fairness analyses and to select important features…

Machine Learning · Computer Science 2024-11-22 Iqbal Madakkatel , Elina Hyppönen

As Artificial Intelligence (AI) is having more influence on our everyday lives, it becomes important that AI-based decisions are transparent and explainable. As a consequence, the field of eXplainable AI (or XAI) has become popular in…

Artificial Intelligence · Computer Science 2024-04-18 Nils Ole Breuer , Andreas Sauter , Majid Mohammadi , Erman Acar

Data Shapley provides a principled approach to data valuation and plays a crucial role in data-centric machine learning (ML) research. Data selection is considered a standard application of Data Shapley. However, its data selection…

Machine Learning · Computer Science 2024-05-08 Jiachen T. Wang , Tianji Yang , James Zou , Yongchan Kwon , Ruoxi Jia

With origins in game theory, probabilistic values like Shapley values, Banzhaf values, and semi-values have emerged as a central tool in explainable AI. They are used for feature attribution, data attribution, data valuation, and more.…

Machine Learning · Computer Science 2026-01-14 R. Teal Witter , Yurong Liu , Christopher Musco

Shapley-related techniques have gained attention as both global and local interpretation tools because of their desirable properties. However, their computation using conditional expectations is computationally expensive. Approximation…

Machine Learning · Statistics 2022-07-13 Zhipu Zhou , Jie Chen , Linwei Hu

Explainable artificial intelligence promises to yield insights into relevant features, thereby enabling humans to examine and scrutinize machine learning models or even facilitating scientific discovery. Considering the widespread technique…

Machine Learning · Computer Science 2026-03-30 Jörg Martin , Stefan Haufe