GraphWorld: Fake Graphs Bring Real Insights for GNNs
Abstract
The continuing maturity of the deep learning subfield of graph neural networks (GNNs) has motivated recent studies into the standard datasets used to benchmark GNNs. While important improvements have been made to GNN datasets and experimental design, any one dataset provides only a singular, potentially spurious insight into the performance of any GNN being tested. We show that state-of-the-art GNN task datasets do not cover the distribution of graphs in a much larger real-data graph repository, with respect to several key graph metrics. Motivated by this finding, we introduce GraphWorld, a novel distributed framework and software package for testing GNN models on an arbitrarily-large population of \emph{synthetic} task datasets.
GraphWorld allows a user to efficiently generate a \emph{world} of millions of graph datasets, with fine-grained control over graph generator parameters, and benchmark arbitrary GNN models, with built-in hyperparameter tuning. Using GraphWorld to generate diverse graph worlds corresponding to node classification, graph classification, and link prediction tasks, we provide insight into the sensitivity of 10,000+ GNN models to various parameters of graphs and node features and} show comparisons between models that have not been possible to make in any previous work. We also introduce a novel metric with which to explore each models' performance on the graph world, conditioning on graph metrics and graph generator parameters.
GraphWorld allows a user to efficiently generate a \emph{world} of millions of graph datasets, with fine-grained control over graph generator parameters, and benchmark arbitrary GNN models, with built-in hyperparameter tuning. Using GraphWorld to generate diverse graph worlds corresponding to node classification, graph classification, and link prediction tasks, we provide insight into the sensitivity of 10,000+ GNN models to various parameters of graphs and node features and} show comparisons between models that have not been possible to make in any previous work. We also introduce a novel metric with which to explore each models' performance on the graph world, conditioning on graph metrics and graph generator parameters.
Research Areas
