no code implementations • ICLR 2022 • David Jaime Tena Cucala, Bernardo Cuenca Grau, Egor V. Kostylev, Boris Motik
In this paper, we propose a new family of GNN-based transformations of graph data that can be trained effectively, but where all predictions can be explained symbolically as logical inferences in Datalog---a well-known knowledge representation formalism.
