English
Related papers

Related papers: The Inverse Shapley Value Problem

200 papers

Explaining AI systems is fundamental both to the development of high performing models and to the trust placed in them by their users. The Shapley framework for explainability has strength in its general applicability combined with its…

Machine Learning · Statistics 2021-12-21 Christopher Frye , Colin Rowat , Ilya Feige

One key problem in network analysis is the so-called influence maximization problem, which consists in finding a set $S$ of at most $k$ seed users, in a social network, maximizing the spread of information from $S$. This paper studies a…

Computer Science and Game Theory · Computer Science 2020-03-19 Ruben Becker , Gianlorenzo D'Angelo , Hugo Gilbert

Reliability-oriented sensitivity analysis methods have been developed for understanding the influence of model inputs relative to events which characterize the failure of a system (e.g., a threshold exceedance of the model output). In this…

Statistics Theory · Mathematics 2025-07-04 Marouane Il Idrissi , Vincent Chabridon , Bertrand Iooss

SHAP (SHapley Additive exPlanations) has become a popular method to attribute the prediction of a machine learning model on an input to its features. One main challenge of SHAP is the computation time. An exact computation of Shapley values…

Machine Learning · Statistics 2023-09-06 Linwei Hu , Ke Wang

Following the work of Lloyd Shapley on the Shapley value, and tangentially the work of Guillermo Owen, we offer an alternative non-probabilistic formulation of part of the work of Robert J. Weber in his 1978 paper "Probabilistic values for…

Theoretical Economics · Economics 2019-05-13 Jacob North Clark , Stephen Montgomery-Smith

Inverse classification uses an induced classifier as a queryable oracle to guide test instances towards a preferred posterior class label. The result produced from the process is a set of instance-specific feature perturbations, or…

Machine Learning · Computer Science 2018-02-15 Michael T. Lash , Qihang Lin , W. Nick Street

Inverse probability weighted estimators are the oldest and potentially most commonly used class of procedures for the estimation of causal effects. By adjusting for selection biases via a weighting mechanism, these procedures estimate an…

Methodology · Statistics 2021-07-06 Ashkan Ertefaie , Nima S. Hejazi , Mark J. van der Laan

Predominately in explainable artificial intelligence (XAI) research, the Shapley value (SV) is applied to determine feature attributions for any black box model. Shapley interaction indices extend the SV to define any-order feature…

Machine Learning · Computer Science 2023-10-31 Fabian Fumagalli , Maximilian Muschalik , Patrick Kolpaczki , Eyke Hüllermeier , Barbara Hammer

The concept of Shannon entropy of random variables was generalized to measurable functions in general, and to simple functions with finite values in particular. It is shown that the information measure of a function is related to the time…

Information Theory · Computer Science 2017-01-25 Guo Zhao

Feature attribution methods help make machine learning-based inference explainable by determining how much one or several features have contributed to a model's output. A particularly popular attribution method is based on the Shapley value…

Artificial Intelligence · Computer Science 2025-11-04 Filip Naudot , Tobias Sundqvist , Timotheus Kampik

Data valuation has become an increasingly significant discipline in data science due to the economic value of data. In the context of machine learning (ML), data valuation methods aim to equitably measure the contribution of each data point…

Machine Learning · Computer Science 2023-06-13 Xiang Li , Haocheng Xia , Jinfei Liu

This paper concerns the analysis of the Shapley value in matching games. Matching games constitute a fundamental class of cooperative games which help understand and model auctions and assignments. In a matching game, the value of a…

Computer Science and Game Theory · Computer Science 2013-07-02 Haris Aziz , Bart de Keijzer

As data becomes the fuel driving technological and economic growth, a fundamental challenge is how to quantify the value of data in algorithmic predictions and decisions. For example, in healthcare and consumer markets, it has been…

Machine Learning · Statistics 2019-06-11 Amirata Ghorbani , James Zou

Shapley values are among the most popular tools for explaining predictions of blackbox machine learning models. However, their high computational cost motivates the use of sampling approximations, inducing a considerable degree of…

Machine Learning · Statistics 2024-04-11 Jeremy Goldwasser , Giles Hooker

We provide a new algorithm for the treatment of inverse problems which combines the traditional SVD inversion with an appropriate thresholding technique in a well chosen new basis. Our goal is to devise an inversion procedure which has the…

Statistics Theory · Mathematics 2016-08-14 Gérard Kerkyacharian , Pencho Petrushev , Dominique Picard , Thomas Willer

We consider the dataset valuation problem, that is, the problem of quantifying the incremental gain, to some relevant pre-defined utility of a machine learning task, of aggregating an individual dataset to others. The Shapley value is a…

Artificial Intelligence · Computer Science 2025-02-25 Felipe Garrido-Lucero , Benjamin Heymann , Maxime Vono , Patrick Loiseau , Vianney Perchet

The dominating set problem has many practical applications but is well-known to be NP-hard. Therefore, there is a need for efficient approximation algorithms, especially in applications such as ad hoc wireless networks. Most distributed…

Physics and Society · Physics 2023-05-16 Hunter Rehm , Robert Kassouf-Short , Puck Rombach

The concept of probabilistic values, such as Beta Shapley values and weighted Banzhaf values, has gained recent attention in applications like feature attribution and data valuation. However, exact computation of these values is often…

Machine Learning · Computer Science 2024-11-01 Weida Li , Yaoliang Yu

Data Shapley has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning. It can effectively identify helpful or harmful data points for a learning algorithm. In this paper, we…

Machine Learning · Computer Science 2022-01-20 Yongchan Kwon , James Zou

Voting systems typically treat all voters equally. We argue that perhaps they should not: Voters who have supported good choices in the past should be given higher weight than voters who have supported bad ones. To develop a formal…

Computer Science and Game Theory · Computer Science 2017-03-16 Nika Haghtalab , Ritesh Noothigattu , Ariel D. Procaccia