Simple Graph Condensation

arXiv:2403.14951v1 Announce Type: new
Abstract: The burdensome training costs on large-scale graphs have aroused significant interest in graph condensation, which involves tuning Graph Neural Networks (GNNs) on a small condensed graph for use on the large-scale original graph. Existing methods primarily focus on aligning key metrics between the condensed and original graphs, such as gradients, distribution and trajectory of GNNs, yielding satisfactory performance on downstream tasks. However, these complex metrics necessitate intricate computations and can potentially disrupt the optimization process …

abstract arxiv costs cs.ai cs.lg cs.si distribution focus gnns graph graph neural networks graphs key metrics networks neural networks scale simple small training training costs type