On the failings of Shapley values for explainability

Cites Work

Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
Unnamed Item
A theory of diagnosis from first principles
Occam's razor
Equational characterizations of Boolean function classes
Interpretable machine learning: fundamental principles and 10 grand challenges
SAT-based rigorous explanations for decision lists
Relation between prognostics predictor evaluation metrics and local interpretability SHAP values
Non-monotonic explanation functions
Explanation in artificial intelligence: insights from the social sciences
A logic for binary classifiers and their explanation
A Way to Simplify Truth Functions
The complexity of logic-based abduction
Analysis of regression in game theory approach
Machine Learning
On Quantifying Literals in Boolean Logic and its Applications to Explainable AI
On Tackling Explanation Redundancy in Decision Trees
On the Tractability of SHAP Explanations
On Cores and Prime Implicants of Truth Functions
The Problem of Simplifying Truth Functions
The Computational Complexity of Understanding Binary Classifier Decisions
A unified logical framework for explanations in classifier systems
Tractability of explaining classifier decisions
Explaining black-box classifiers: properties and functions
A logic of ``black box classifier systems
On computing probabilistic abductive explanations
On the (complete) reasons behind decisions
Explanation of pseudo-Boolean functions using cooperative game theory and prime implicants
A Symbolic Approach for Counterfactual Explanations
Certified logic-based explainable AI -- the case of monotonic classifiers
Feature necessity \& relevancy in ML classifier explanations
Towards formal XAI: formally approximate minimal explanations of neural networks
A new class of explanations for classifiers with non-binary features