Characterizing the Influence of Topology on Graph Learning Tasks

arXiv:2404.07493v1 Announce Type: new
Abstract: Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations. However, the fundamental problem of understanding and analyzing how graph topology influences the performance of learning models on downstream tasks has not yet been well understood. In this paper, we propose a metric, TopoInf, which characterizes the influence of graph topology by measuring the level of compatibility between the topological information …

abstract arxiv cs.ai cs.lg encoding features gnn graph graph learning graph neural networks however influence networks neural networks performance success tasks topology type understanding