21 datasets found

The dataset used in the paper is a real-world dataset for future link prediction task on dynamic graphs.

Graphs are essential representations of many real-world data such as social networks. Recent years have witnessed the increasing efforts made to extend the neural network models...

Temporal Knowledge Graph (TKG) datasets for link prediction task

The dataset used in the paper is a link prediction benchmark dataset (Cora, PubMed, Disease, Airport) with a Gromov θ-hyperbolicity value.

Knowledge graphs are composed of different elements: entity nodes, relation edges, and literal nodes. Each literal node contains an entity’s attribute value (e.g. the height of...

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

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

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

The dataset used in the paper is Twitter and Foursquare, two real-world aligned heterogeneous social networks.

OGB-MAG is a large-scale dataset used for node classification and link prediction.

DBLP, IMDB, ACM, and Freebase are four public datasets used for node classification and link prediction.

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data.

Representing entities and relations in an embedding space is a well-studied approach for machine learning on relational data.

Knowledge graphs (KGs) are collections of facts. Some well-known knowledge graphs include Freebase (Bollacker et al., 2008), Word-Net (Miller, 1995), YAGO (Suchanek et al.,...

Knowledge graphs store a wealth of knowledge from the real world into structured graphs, which consist of collections of triplets, and each triplet (h, r, t) represents that...

The dataset used in the paper is a multi-graph problem, where each graph represents a different network. The dataset is used to evaluate the performance of the RECS algorithm on...

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 Cora and Citeseer datasets are used for training machine learning models to classify documents into different categories.

A bipartite interaction graph that contains the edits on Wikipedia pages over a month.

The dataset used in the paper is a heterogeneous graph, which is a graph that contains multiple types of nodes and edges. The dataset is used for semi-supervised graph learning...