Node classification

15 datasets tagged as the tag “Node classification”.

15 datasets.

Twitch Gamers Social Network Analyzed

A Twitch (gaming social network) dataset of 168,116 users and 6,797,558 mutual follower edges, collected by Rozemberczki & Sarkar via Twitch public API (2018). Each record contains undirected mutual follower edges, node features (views, mature, life_time, created_at, updated_at, dead_account, language, affiliate). The dataset is notable for its large-scale strongly connected component with no missing attributes, designed for node classification and count data regression. Intended for research into social network analysis, node classification, community detection, and transfer learning in gaming communities.

168.1K records168.1K nodes6.8M edges2021

GEMSEC Facebook Page-Page Networks (Cumulative) Analyzed

A Facebook (social media platform) dataset of 134,833 Facebook pages and 1,379,403 undirected mutual-like edges across 8 page categories (company, politician, tvshow, government, artist, new_sites, public_figure, athletes), collected by Rozemberczki et al. via Facebook Graph API, distributed via GEMSEC/SNAP. Each record contains undirected edges between Facebook pages representing mutual likes; pages categorized as company, politician, TV show, government, artist, news site, public figure, or athlete; node IDs namespaced by category. The dataset is notable for its multi-category Facebook page network with known ground-truth category labels per node, enabling direct evaluation of community detection and node classification algorithms across heterogeneous page types. Intended for research into community detection, node classification, graph embedding, cross-category network comparison, and social media page recommendation research.

134.8K records134.8K nodes1.4M edges2019

BlogCatalog (v2) Friendship Network Analyzed

A BlogCatalog (v2) dataset of 97,884 bloggers and 1,668,698 friendship edges, collected by Agarwal et al. / Tang & Liu via BlogCatalog crawl. Each record contains blogger-blogger friendship edges, user IDs. The dataset is notable for its blogosphere friendship network from BlogCatalog, used for familiar stranger detection and latent social dimensions research. Intended for research into social network analysis, community detection, group membership prediction, and blogosphere structure studies.

97.9K records97.9K nodes1.7M edges2009

Flickr Friendship + Group Network Analyzed

A Flickr (photo-sharing) dataset of 80,513 users and 5,899,882 friendship edges, collected by Tang & Liu via Flickr crawl (2009). Each record contains user-user friendship edges, group memberships (195 groups), and user IDs. The dataset is notable for its classic photo-sharing social network with explicit group memberships, used as a benchmark for latent social dimensions. Intended for research into social network analysis, community detection, group membership prediction, and photo-sharing platform structure studies.

80.5K records80.5K nodes5.9M edges2009

Cora Citation Network Analyzed

A Cora machine learning paper database dataset of 23,166 nodes and 91,500 edges, collected by McCallum et al.. Each record contains directed: True, weighted: False. Classic citation network of machine learning papers — one of the most used benchmarks for graph neural network node classification.. Suitable for graph neural networks, node classification, citation network analysis.

23.2K records23.2K nodes91.5K edges2013

PubMed Network (GCN Benchmark) Analyzed

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.

19.7K records19.7K nodes44.3K edges2016

BlogCatalog (v3) Friendship + Group Network Analyzed

A BlogCatalog (v3) dataset of 10,312 bloggers and 333,983 friendship edges, collected by Agarwal et al. / Tang & Liu via BlogCatalog crawl. Each record contains blogger-blogger friendship edges, user IDs and group memberships. The dataset is notable for its blogosphere friendship network from BlogCatalog, used for familiar stranger detection and latent social dimensions research. Intended for research into social network analysis, community detection, group membership prediction, and blogosphere structure studies.

10.3K records10.3K nodes334K edges2009

CiteSeer Network (GCN Benchmark) Analyzed

A CiteSeer dataset of 3,327 nodes, 4,676 edges, 6 classes, collected by Yang et al. (ICML 2016). Each record contains node features, citation edges, class labels. CiteSeer network with bag-of-words features. Suitable for node classification, semi-supervised learning, graph neural networks.

3.3K records3.3K nodes4.7K edges2016

Cora Network (GCN Benchmark) Analyzed

A Cora dataset of 2,708 nodes, 5,278 edges, 7 classes, collected by Yang et al. (ICML 2016). Each record contains node features, citation edges, class labels. Cora network with bag-of-words features. Suitable for node classification, semi-supervised learning, graph neural networks.

2.7K records2.7K nodes5.3K edges2016

Terrorist Relations Network (GCN Benchmark) Analyzed

A Terrorist Relations dataset of 881 nodes, 8,592 edges, 4 classes, collected by Yang et al. (ICML 2016). Each record contains node features, citation edges, class labels. Terrorist Relations network with bag-of-words features. Suitable for node classification, semi-supervised learning, graph neural networks.

881 records881 nodes8.6K edges2006

Terrorist Attacks Network (GCN Benchmark) Analyzed

A Terrorist Attacks dataset of 645 nodes, 3,172 edges, 6 classes, collected by Yang et al. (ICML 2016). Each record contains node features, citation edges, class labels. Terrorist Attacks network with bag-of-words features. Suitable for node classification, semi-supervised learning, graph neural networks.

645 records645 nodes3.2K edges2006

WebKB Wisconsin WebKB (GCN Benchmark) Analyzed

A WebKB wisconsin dataset of 265 web pages, 479 hyperlinks, collected by Yang et al. (ICML 2016). Each record contains web page features, hyperlink edges, class labels. WebKB wisconsin university web page classification dataset. Suitable for node classification, web page categorization, graph neural networks.

265 records265 nodes479 edges2000

WebKB Washington WebKB (GCN Benchmark) Analyzed

A WebKB washington dataset of 230 web pages, 417 hyperlinks, collected by Yang et al. (ICML 2016). Each record contains web page features, hyperlink edges, class labels. WebKB washington university web page classification dataset. Suitable for node classification, web page categorization, graph neural networks.

230 records230 nodes417 edges2000

WebKB Cornell WebKB (GCN Benchmark) Analyzed

A WebKB cornell dataset of 195 web pages, 286 hyperlinks, collected by Yang et al. (ICML 2016). Each record contains web page features, hyperlink edges, class labels. WebKB cornell university web page classification dataset. Suitable for node classification, web page categorization, graph neural networks.

195 records195 nodes286 edges2000

WebKB Texas WebKB (GCN Benchmark) Analyzed

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.

187 records187 nodes298 edges2000