19 datasets found

The datasets used in the paper are Blog1, Blog2, Citationv1, DBLPv7, and ACMv9.

The Political Blogs dataset is a list of political blogs from 2004 US Election classified as liberal or conservative, and links between the blogs.

The dataset used in the paper is the faculty friendship network.

The dataset used in the paper is the Enron email network.

The dataset is used to analyze the evolution of beliefs in social networks. It contains three cases: static network, randomly changing network, and homophily-based dynamic network.

DeepWalk: Online Learning of Social Representations

The LiveJournal dataset is a free online blogging social network of around 4 million users.

The Political Blogs dataset contains a list of political blogs from the 2004 US Election classified as liberal or conservative, and links between blogs.

The dataset used in the paper is a social network dataset, which contains user interactions and popularity data.

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

The dataset is used to discover hierarchical relationships from unstructured observations, specifically in the setting of discovering pairwise hierarchical relations between...

The DBLP dataset contains full paper texts with 2,874,303 citations in the field of computer science.

The dataset used in the paper is a collection of explicit interactions gathered from various sources, including music websites, movie ratings, book clubs, social networks, and...

The WebKB dataset is a collection of web pages from the University of Washington's Knowledge Base, with each page annotated with a set of labels.

Gowalla is a social network where users can check-in to locations.

The BlogCatalog dataset is a blog directory that manages bloggers and their blogs. Each unit is a blogger and the features are bag-of-words representations of keywords in...

The Pokec dataset is a social network dataset.

The IMDB-B and IMDB-M datasets are used to evaluate the transferability of the proposed GNAE model.

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