Paper proposes a uniqueness Shapley measure to compare variable importance.
problem Comparing the importance of different variables in identifying subjects.
method Uses Shapley value to combine reductions in log cardinality due to revealing variables.
result Demonstrates speedup in calculating variable importance.
The paper develops axioms for uniquely decomposing functions with real arguments.
problem Decomposing functions with real arguments while preserving their overall structure.
method Developing axioms to uniquely decompose Borel measurable functions.
result Unique decompositions for all Borel measurable functions are achieved.
The paper explores how Shapley value for a feature can vary based on model outcomes and feature distribution.
problem The uniqueness of Shapley value in explaining model predictions.
method Analyzes the relationship between feature distribution and Shapley value, and compares Shapley values for different model outcomes.
result Shapley value for a feature depends on more than just its mean and can vary significantly based on model outcome.
Mathematical proofs for Shapley explanations clarify their properties.
problem Clarify the essential axioms and properties of Shapley values in machine learning.
method Mathematical rigor and axiomatic characterization.
result The symmetry axiom is essential for Shapley values, contradicting Lundberg and Lee's claim.
Introduces joint Shapley values to measure feature importance in models.
problem Measuring the importance of feature sets in machine learning models.
method Extends Shapley's axioms to measure a set of features' average contribution to a model's prediction.
result Joint Shapley values provide unique insights and are more consistent with local intuitions.
"How much is my data worth?" is an increasingly common question posed by organizations and individuals alike. An answer to this question could allow, for instance, fairly distributing profits among multiple data contributors and determining prospective compensation when data breaches happen. In this paper, we study the…
The problem of explaining the behavior of deep neural networks has recently gained a lot of attention. While several attribution methods have been proposed, most come without strong theoretical foundations, which raises questions about their reliability. On the other hand, the literature on cooperative game theory sugg…
FGSV defends against shell company attacks in group data valuation.
problem Shell company attacks on group-level data valuation.
method Developed a provably fast and accurate approximation algorithm for FGSV.
result Empirical results show significant improvement in computational efficiency and accuracy.
New Shapley values reveal non-linear feature dependencies.
problem Understanding non-linear dependencies in machine learning models.
method Model-independent Shapley values using non-parametric measures of dependence.
result Model-independent Shapley values can uncover non-linear dependencies.
Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models. These methods define a cooperative game between the features of a model and distribute influence among these input elements using some form of the game's unique Shapley values. Justification for these me…
Shapley Flow interprets model predictions using a graph-based approach to feature importance.
problem Existing feature importance methods ignore or hide feature dependencies.
method Shapley Flow considers the entire causal graph and assigns credit to edges.
result Shapley Flow provides a deeper, graph-based view of feature importance.
New foundation for Shapley value immune to coalitional manipulations.
problem Coalitional manipulations in game theory.
method Revised Shapley value criteria for coalitional games.
result Shapley value is immune to coalitional manipulations under new criteria.
A new method simplifies feature explanation for complex models.
problem Explain predictions from complex models efficiently with many features.
method groupShapley: groups features for Shapley value computation.
result Equivalent to summing feature-wise Shapley values within groups.
The study compares different game-theoretic attribution methods and finds that interventional Shapley values yield less consistent results than Aumann-Shapley due to path symmetry.
problem Investigating the influence of path choice on game-theoretic attribution algorithms.
method Comparative analysis of interventional Shapley values and Generalized Integrated Gradients (GIG) methods.
result Interventional Shapley values yield less consistent attributions than Aumann-Shapley due to path symmetry and extended away from the training data manifold.
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 suggested that individuals should be compensated for the data that they generate, but it…
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 precise, rigorous foundation: it provides a common, model-agnostic language for AI e…
New method decomposes profits and losses continuously, avoiding discrete reporting issues.
problem Analyzing profits and losses at discrete dates ignores detailed paths.
method Constructs a large class of continuous-time decompositions using extended Itô's formula.
result Identifies a preferred decomposition from exactness, symmetry, and normalization axioms.
Signed pairwise interactions conflate uniqueness, redundancy, and synergy
problem Signed pairwise interactions conflate uniqueness, redundancy, and synergy
method Stochastic Hi-Fi
result Stochastic Hi-Fi recovers structure missed by scalar baselines
SVEHNN explains DNN diagnoses of Alzheimer's disease from neuroanatomy and biomarkers.
problem Interpreting deep neural networks for medical diagnosis, especially in the clinic.
method Shapley Value Explanation of Heterogeneous Neural Networks (SVEHNN) for local explanations.
result SVEHNN provides interpretable explanations for DNN diagnoses with reduced runtime.
Paper improves KNN-Shapley for privacy-friendly data valuation.
problem Privacy challenges in data valuation methods.
method Introduces TKNN-Shapley, a privacy-friendly variant of KNN-Shapley.
result TKNN-Shapley offers superior privacy-utility tradeoff compared to naively privatized KNN-Shapley.
Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data summarization and domain adaption. One simple idea is to use the leave-one-out error of each training …
Shapley values criticized for feature selection, leading to new insights.
problem Using Shapley values for feature selection is problematic.
method Introduced and critiqued Shapley values as feature selection tools, using counterexamples and simulations.
result Shapley values may not always align with feature selection goals.
Unified and noise-reduced data valuation framework for machine learning.
problem Quantifying the contribution of individual data points in machine learning.
method Beta Shapley, a generalization of Data Shapley, relaxes the efficiency axiom.
result Beta Shapley outperforms state-of-the-art data valuation methods on various ML tasks.
Shapley value improves model interpretation but not causal inference.
problem Improving model interpretability without losing predictive power.
method Analyzed Shapley value in Bayesian networks, linking it to conditional independence.
result Eliminating high Shapley value variables does not harm predictive performance, but low Shapley value variables can.
New method calculates Shapley values for uncertain functions.
problem Uncertain value functions in explainable machine learning.
method Definition of Shapley values using probability theory.
result Shapley values can be applied to uncertain functions.
New insights on Shapley value precision for tabular data predictions.
problem Precision of Shapley value explanations for individual observations.
method Conditional Shapley value estimation methods for tabular data.
result Shapley value explanations are less precise for outer observations.
Efficient WKNN-Shapley computation improves data valuation accuracy.
problem Efficient computation of Data Shapley for WKNN algorithm.
method Reframed WKNN-Shapley as a counting problem, introduced quadratic-time algorithm.
result Quadratic-time WKNN-Shapley computation, improving from O(NK). Study reveals Data Shapley's inconsistent performance in data selection tasks.
problem Inconsistency of Data Shapley's performance in data selection across different settings.
method Hypothesis testing framework and identification of utility functions.
result Data Shapley's performance is no better than random selection without specific constraints.
Unified framework for calculating Shapley values with correlated features.
problem Inaccurate Shapley values due to multicollinearity.
method Unified framework with matrix formulation and mathematical proof.
result Shapley values become independent of feature correlations.
The paper introduces Absolute Shapley Value to handle negative contributions in machine learning model training.
problem Negative marginal contributions in machine learning model training.
method Investigates three philosophies: Original Shapley Value, Zero Shapley Value, and Absolute Shapley Value.
result Absolute Shapley Value significantly outperforms other definitions in evaluating data importance.
Develops Shapley explainability solutions respecting data manifold.
problem Tenable assumption of uncorrelated features in Shapley explainability.
method Two solutions: generative modelling and direct learning of Shapley value-function.
result On-manifold Shapley explainability overcomes drawbacks of 'off-manifold' values.
SIM-Shapley improves SV approximation efficiency and stability.
problem High computational costs of Shapley value methods in high-dimensional settings.
method Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley).
result Reduced computation time by up to 85% while maintaining feature attribution quality.
We introduce a variable importance measure to quantify the impact of individual input variables to a black box function. Our measure is based on the Shapley value from cooperative game theory. Many measures of variable importance operate by changing some predictor values with others held fixed, potentially creating unl…
Paper proposes using tree-based surrogate models for efficient Shapley computation.
problem Efficient computation of Shapley values using conditional expectations.
method Surrogate model-based tree for approximating Shapley and SHAP values.
result The proposed algorithm improves accuracy and unifies global interpretation.
New sampling method estimates Shapley values more accurately.
problem Exponential time complexity of computing Shapley values.
method Multilinear sampling algorithm based on game theory.
result Our method reduces variance and provides more accurate Shapley value estimations.
SHAFF estimates Shapley effects efficiently even with dependent variables.
problem Challenges in estimating Shapley effects, especially with dependent variables.
method SHAFF uses random forests to estimate Shapley effects efficiently.
result SHAFF provides a fast and accurate estimate of Shapley effects.
FastSHAP speeds up Shapley value estimation for black-box models.
problem Efficiently calculating Shapley values for complex models.
method Uses a learned explainer model in a single forward pass.
result Generates high-quality explanations with significant speedup.
This paper proposes a new method to fairly value data in federated learning.
problem Fairly valuing decentralized data contributions in federated learning.
method Variant of Shapley value (federated Shapley value) that is efficient and respects the order of data contributions.
result The federated Shapley value can reflect the real utility of data sources and enhance system robustness, security, and efficiency.
Proposes a new method to avoid model extrapolation in Shapley values.
problem Model extrapolation in marginal Shapley values leads to unreliable explanations.
method Proposes a new approach that avoids model extrapolation using marginal averaging and causal information.
result Demonstrates the impacts of model extrapolation on Shapley values and proposes a new method to avoid it.
Paper uses VAEAC to estimate Shapley values for complex models with mixed features.
problem Estimating Shapley values for models with dependent mixed features.
method Uses variational autoencoder with arbitrary conditioning (VAEAC) to model feature dependencies.
result VAEAC approach outperforms state-of-the-art methods for various settings.
We introduce a new method to explain Gaussian processes using Shapley values.
problem Explaining the uncertainty in Gaussian process models.
method Extending Shapley values to stochastic cooperative games for Gaussian processes.
result Our method generates explanations that are random variables and satisfy favorable axioms.
Paper proves Shapley value convergence in Bayesian learning games.
problem Measuring contributions in cooperative games using Bayesian inference.
method Established convergence of Shapley value in parametric Bayesian learning games.
result Shapley value differences converge in probability to a limiting game.
Study uses Shapley value for sensor anomaly detection, proving its superiority in certain cases.
problem Anomaly detection in sensor networks using the Shapley value.
method Optimized binary classifiers, mathematical proofs for different scenarios.
result Shapley value test can be superior or inferior to single-term tests, depending on sensor correlation and attack type.
The paper introduces Shapley curves for measuring variable importance in nonparametric settings.
problem Limited statistical understanding of Shapley values as variable importance measures.
method Introduces Shapley curves based on conditional expectation and covariate distribution; derives convergence rates and normality; proposes a novel bootstrap procedure.
result Validates theoretical findings with numerical studies and analyzes vehicle prices determinants.
This paper proposes an efficient method for calculating Shapley values in Naive Bayes classifiers.
problem The need for explaining machine learning model decisions.
method An exact analytic expression of Shapley values for Naive Bayes classifiers.
result The proposed Shapley values provide informative results with low complexity and low computation time.
We propose a novel Shapley value approach to help address neural networks' interpretability and "vanishing gradient" problems. Our method is based on an accurate analytical approximation to the Shapley value of a neuron with ReLU activation. This analytical approximation admits a linear propagation of relevance across …
A new method for efficiently estimating Shapley values in dataset valuation.
problem Quantifying the incremental gain of individual datasets in machine learning tasks.
method Discrete uniform Shapley value approximation.
result Proposes a more efficient method for Shapley value estimation.
The Shapley value theory is used for risk allocation in non-orthogonal risk factors.
problem Risk allocation among non-orthogonal risk factors in financial portfolios.
method Using Shapley value from cooperative game theory to allocate risk contributions.
result Explicit formulas and numerical algorithms for calculating risk allocations are derived.