Shapley value: from cooperative game to explainable artificial intelligence

With the tremendous success of machine learning (ML), concerns about their black-box nature have grown. The issue of interpretability affects trust in ML systems and raises ethical concerns such as algorithmic bias. In recent years, the feature attribution explanation method based on Shapley value has become the mainstream explainable artificial intelligence approach for explaining ML models. This paper provides a comprehensive overview of Shapley value-based attribution methods. We begin by outlining the foundational theory of Shapley value rooted in cooperative game theory and discussing its desirable properties. To enhance comprehension and aid in identifying relevant algorithms, we propose a comprehensive classification framework for existing Shapley value-based feature attribution methods from three dimensions: Shapley value type, feature replacement method, and approximation method. Furthermore, we emphasize the practical application of the Shapley value at different stages of ML

Shapley value: from cooperative game to explainable artificial intelligence Review Open access Published: 09 February 2024 Volume 4 , article number 2 ( 2024 ) Cite this article You have full access to this open access article Download PDF Save article View saved research Autonomous Intelligent Systems Aims and scope Submit manuscript Shapley value: from cooperative game to explainable artificial intelligence Download PDF Abstract With the tremendous success of machine learning (ML), concerns about their black-box nature have grown. The issue of interpretability affects trust in ML systems and

saved by

• 4665

related reading

• Explaining Neural Network Models with SHAP Values: A Mathematical Perspective | by Kevin Akbari | Mediumakbarikevin.medium.com
• 6 – Interpretability – Machine Learning Blog | ML@CMU | Carnegie Mellon Universityblog.ml.cmu.edu
• Dario Amodei — The Urgency of Interpretabilitydarioamodei.com
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• An Ambitious Vision for Interpretability — AI Alignment Forumalignmentforum.org
• [2403.10415] Gradient based Feature Attribution in Explainable AI: A Technical Reviewar5iv.labs.arxiv.org
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
• I: Data problems (and solution concepts) in MLml-data-tutorial.org
• Shapley value - Wikipediaen.wikipedia.org
• The Hitchhiker's Guide to Actionable Interpretabilityactionable-interpretability-guide.github.io