Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure

arXiv:2301.10956v4 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) are popular models for graph learning problems. GNNs show strong empirical performance in many practical tasks. However, the theoretical properties have not been completely elucidated. In this paper, we investigate whether GNNs can exploit the graph structure from the perspective of the expressive power of GNNs. In our analysis, we consider graph generation processes that are controlled by hidden (or latent) node features, which contain all information about the graph structure. …

abstract arxiv cs.lg cs.si exploit features gnns graph graph learning graph neural networks hidden however networks neural networks paper performance popular practical show tasks the graph type