myerson 0.1.5

A python package to calculate Myerson values from game theory and use them as explanations for graph neural networks.

Calculate Myerson values and explain GNNs

This package implements the Myerson solution concept from cooperative game theory. The Myerson values attribute every player of a game their fair contribution to the games payoff. Myerson values are related to Shapley values but the player cooperation is restricted by a graph.

A graph neural network (GNN) can be treated as a coalition function for a game and the Myerson values can be used as feature attribution explanations to understand a model prediction. This package also implements Methods to explain PyG GNNs with Myerson values.

Calculating the Myerson value scales exponentially with bigger graphs / more players. Therfore, Monte Carlo sampling techniques were implemented to approximate the Myerson values.

Installation

Install the package with the following command:

pip install myerson

Examples and Documentation

Example uses can be found here. The full documentation can be found at https://myerson.readthedocs.io/.

Citation

TBD.