Home » Publication » 25566

Dettaglio pubblicazione

2022, ISCIENCE, Pages -

EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks (01a Articolo in rivista)

Mastropietro Andrea, Pasculli Giuseppe, Feldmann Christian, Rodríguezpérez Raquel, Bajorath Jürgen

Graph neural networks (GNNs) recursively propagate signals along the edges of an input graph, integrate node feature information with graph structure, and learn object representations. Like other deep neural network models, GNNs have notorious black box character. For GNNs, only few approaches are available to rationalize model decisions. We introduce EdgeSHAPer, a generally applicable method for explaining GNN-based models. The approach is devised to assess edge importance for predictions. Therefore, EdgeSHAPer makes use of the Shapley value concept from game theory. For proof-of-concept, EdgeSHAPer is applied to compound activity prediction, a central task in drug discovery. EdgeSHAPer’s edge centricity is relevant for molecular graphs where edges represent chemical bonds. Combined with feature mapping, EdgeSHAPer produces intuitive explanations for compound activity predictions. Compared to a popular node-centric and another edge-centric GNN explanation method, EdgeSHAPer reveals higher resolution in differentiating features determining predictions and identifies minimal pertinent positive feature sets
Gruppo di ricerca: Algorithms and Data Science
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma