Abstract: This paper presents a novel algorithm for computing the eigenvector associated with either the largest or the smallest eigenvalue of a complex Hermitian matrix. This type of algorithm is ...
tl;dr: We provably improve GNN expressivity by enhancing message passing with substructure encodings. Our method allows incorporating domain specific prior knowledge and can be used as a drop-in ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback