Scalable Privacy-enhanced Benchmark Graph Generative Model for Graph Convolutional Networks. (arXiv:2207.04396v1 [cs.LG])

A surge of interest in Graph Convolutional Networks (GCN) has produced
thousands of GCN variants, with hundreds introduced every year. In contrast,
many GCN models re-use only a handful of benchmark datasets as many graphs of
interest, such as social or commercial networks, are proprietary. We propose a
new graph generation problem to enable generating a diverse set of benchmark
graphs for GCNs following the distribution of a source graph -- possibly
proprietary -- with three requirements: 1) benchmark effectiveness …

benchmark lg networks privacy