Graph as Point Set

arXiv:2405.02795v1 Announce Type: new
Abstract: Graph is a fundamental data structure to model interconnections between entities. Set, on the contrary, stores independent elements. To learn graph representations, current Graph Neural Networks (GNNs) primarily use message passing to encode the interconnections. In contrast, this paper introduces a novel graph-to-set conversion method that bijectively transforms interconnected nodes into a set of independent points and then uses a set encoder to learn the graph representation. This conversion method holds dual significance. Firstly, it …

abstract arxiv contrast conversion cs.lg current data encode fundamental gnns graph graph neural networks independent learn networks neural networks nodes novel paper set stores type