5 datasets tagged as the tag “Benchmark graph”.
5 datasets.
A PubMed dataset of 19,717 nodes, 44,327 edges, 3 classes, collected by Yang et al. (ICML 2016). Each record contains node features, citation edges, class labels. PubMed network with bag-of-words features. Suitable for node classification, semi-supervised learning, graph neural networks.
A WebKB texas dataset of 187 web pages, 298 hyperlinks, collected by Yang et al. (ICML 2016). Each record contains web page features, hyperlink edges, class labels. WebKB texas university web page classification dataset. Suitable for node classification, web page categorization, graph neural networks.
A Bottlenose dolphin community (Doubtful Sound, New Zealand) dataset of 62 nodes and 159 edges, collected by D. Lusseau et al.. Each record contains directed: False, weighted: False, signed: False. Classic benchmark: 62 bottlenose dolphins with frequent associations — widely used to validate community detection algorithms.. Suitable for community detection benchmark, animal social network analysis.
A University karate club (W.W. Zachary observation study) dataset of 34 nodes and 78 edges, collected by W.W. Zachary. Each record contains directed: False, weighted: False, signed: False. The most widely cited network in graph research — 34-node karate club that split into two factions, used to validate virtually every community detection algorithm.. Suitable for community detection benchmark, foundational social network analysis.
A NDS-VU signed network repository dataset of 19 nodes and 125 signed edges from a monastery social network, collected by Sampson (1969), distributed by NDS-VU. Each record contains directed signed edges between nodes: sign (+1 or -1) representing positive/negative relationships; no edge weights beyond binary sign. Classic small signed social network from a monastery study by Sampson (1969), widely used as a benchmark for signed community detection and balance theory validation. Suitable for signed network analysis, balance theory, community detection benchmarking.
WebKB