Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach
Summary: Here we present EdgeSHAPer, a workflow for explaining graph neural networks by approximating Shapley values using Monte Carlo sampling. In this protocol, we describe steps to execute Python scripts for a chemical dataset from the original publication; however, this approach is also applicab...
Main Authors: | Andrea Mastropietro, Giuseppe Pasculli, Jürgen Bajorath |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | STAR Protocols |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666166722007675 |
Similar Items
-
EdgeSHAPer: Bond-centric Shapley value-based explanation method for graph neural networks
by: Andrea Mastropietro, et al.
Published: (2022-10-01) -
Protocol to explain support vector machine predictions via exact Shapley value computation
by: Andrea Mastropietro, et al.
Published: (2024-06-01) -
Calculation of exact Shapley values for explaining support vector machine models using the radial basis function kernel
by: Andrea Mastropietro, et al.
Published: (2023-11-01) -
Explaining Multiclass Compound Activity Predictions Using Counterfactuals and Shapley Values
by: Alec Lamens, et al.
Published: (2023-07-01) -
Calculation of exact Shapley values for support vector machines with Tanimoto kernel enables model interpretation
by: Christian Feldmann, et al.
Published: (2022-09-01)