Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach

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 applicable to any...

Descripción completa

Detalles Bibliográficos
Autores principales: Mastropietro, Andrea, Pasculli, Giuseppe, Bajorath, Jürgen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Protocol
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9700376/
https://www.ncbi.nlm.nih.gov/pubmed/36595907
http://dx.doi.org/10.1016/j.xpro.2022.101887

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9700376/
https://www.ncbi.nlm.nih.gov/pubmed/36595907
http://dx.doi.org/10.1016/j.xpro.2022.101887

Ejemplares similares