A Amazon (co-purchasing network) dataset of 334,863 nodes and 925,872 edges, collected by Yang & Leskovec from Amazon website (2012). Each record contains product-product co-purchasing edges and product-category communities. The dataset is notable for its product co-purchasing network with ground-truth communities from categories. Intended for research into community detection, recommendation systems, and product relationship analysis.
A DBLP (co-authorship network) dataset of 317,080 nodes and 1,049,866 edges, collected by Yang & Leskovec from DBLP bibliography (2012). Each record contains author-author co-authorship edges and publication-venue communities. The dataset is notable for its academic collaboration network with ground-truth communities from publication venues. Intended for research into community detection, network evolution, and scientific collaboration analysis.