On the Topology Awareness and Generalization Performance of Graph Neural Networks

arXiv:2403.04482v1 Announce Type: new
Abstract: Many computer vision and machine learning problems are modelled as learning tasks on graphs, where graph neural networks (GNNs) have emerged as a dominant tool for learning representations of graph-structured data. A key feature of GNNs is their use of graph structures as input, enabling them to exploit the graphs' inherent topological properties-known as the topology awareness of GNNs. Despite the empirical successes of GNNs, the influence of topology awareness on generalization performance remains unexplored, …

abstract arxiv computer computer vision cs.lg data feature gnns graph graph neural networks graphs key machine machine learning networks neural networks performance structured data tasks tool topology type vision