21 datasets found

Formats: JSON Tags: Link Prediction

Filter Results

  • COLLAB

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

  • Streaming Graph Neural Networks

    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...

  • ICEWS14 and ICEWS05-15

    Temporal Knowledge Graph (TKG) datasets for link prediction task

  • Disease

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

  • YAGO3-10

    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...

  • LiveJournal

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

  • Gplus

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

  • Facebook

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

  • Twitter and Foursquare

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

  • OGB-MAG

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

  • DBLP, IMDB, ACM, and Freebase

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

  • ConvE

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

  • DistMult

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

  • FB15k-237

    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.,...

  • WN18RR

    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...

  • Flickr

    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...

  • BlogCatalog

    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...

  • Cora and Citeseer datasets

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

  • Wiki

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

  • ACM

    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...
You can also access this registry using the API (see API Docs).