ShapG: new feature importance method based on the Shapley value

TL;DR

ShapG is a new model-agnostic XAI method that efficiently computes feature importance using a graph-based approximation of Shapley values, improving accuracy and speed over existing methods.

Contribution

Introduces ShapG, a novel graph-based sampling approach for calculating Shapley values, enhancing explanation accuracy and computational efficiency in AI models.

Findings

ShapG provides more accurate feature importance explanations.

ShapG has faster computation time compared to existing XAI methods.

ShapG demonstrates wide applicability across different complex models.

Abstract

With wide application of Artificial Intelligence (AI), it has become particularly important to make decisions of AI systems explainable and transparent. In this paper, we proposed a new Explainable Artificial Intelligence (XAI) method called ShapG (Explanations based on Shapley value for Graphs) for measuring feature importance. ShapG is a model-agnostic global explanation method. At the first stage, it defines an undirected graph based on the dataset, where nodes represent features and edges are added based on calculation of correlation coefficients between features. At the second stage, it calculates an approximated Shapley value by sampling the data taking into account this graph structure. The sampling approach of ShapG allows to calculate the importance of features efficiently, i.e. to reduce computational complexity. Comparison of ShapG with other existing XAI methods shows that it provides more accurate explanations for two examined datasets. We also compared other XAI methods developed based on cooperative game theory with ShapG in running time, and the results show that ShapG exhibits obvious advantages in its running time, which further proves efficiency of ShapG. In addition, extensive experiments demonstrate a wide range of applicability of the ShapG method for explaining complex models. We find ShapG an important tool in improving explainability and transparency of AI systems and believe it can be widely used in various fields.