17 datasets found

The dataset is used for analyzing time-varying financial networks extracted from the New York Stock Exchange (NYSE) dataset.

Real social network datasets provide significant benefits for understanding phenomena such as information diffusion or network evolution. Yet the privacy risks raised from...

The dataset used in this paper is the Amazon instances, which are a collection of networks representing the relationships between users and items on the Amazon website.

The dataset used in this study is a symptom network constructed from a large-scale dataset of psychological screening data collected from university students.

The TUDataset is a collection of benchmark datasets for learning with graphs. It contains 14 datasets, each with a different type of graph.

The Cora citation network dataset is used to evaluate the performance of graph embedding methods on real-world data.

The Facebook Social Circles dataset contains information about the social connections between users on Facebook.

Matrix factorization (MF) and Autoencoder (AE) are among the most successful approaches of unsupervised learning.

Synwalk - Community Detection via Random Walk Modelling

The email communication network at the University Rovira i Virgili in Tarragona in the south of Catalonia in Spain.

The dataset contains traffic and network characteristics of fake and real news sites.

The dataset contains 283 fake news sites, along with their traffic and network characteristics.

A large-scale dataset of tweets, retweets, user activity history, and follower networks, comprising over 161 million tweets from more than 41 million unique users.

Real-world datasets used for empirical studies, including Cora, CiteSeer, and PubMed.

The dataset used in the paper to evaluate the influence of graph elements on the parameter changes of GCNs without needing to retrain the GCNs.

The dataset used in the paper to evaluate the influence of graph elements on the parameter changes of GCNs without needing to retrain the GCNs.

The dataset used in this paper is the CORA citation network, a directed graph with 19,793 vertices and 27,225 edges.