83 datasets found

CORA, Citeseer, Pubmed, OGB arXiv

The dataset used in the paper is a collection of nine graphs with different degrees of homophily.

The dataset used in the paper is a comprehensive survey on graph neural networks.

The dataset used in the paper is a collection of six low-homophily node classification tasks.

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...

Graph representation learning typically aims to learn an informative embedding for each graph node based on the graph topology (link) information.

Graph Neural Networks (GNNs) have become a popular approach for various applications, ranging from social network analysis to modeling chemical properties of molecules.

The Temporal Occupancy Flow Graph (TOFG) is a unified environment representation that unifies the map information and vehicle trajectories in a homogeneous graph.

Table Extraction (TE) is redefined as a node classification task, addressed by a GNN. Graph nodes are composed of basic PDF objects while edges are computed considering...

The authors used the Moleculenet dataset for their experiments.

The authors used the TEXAS dataset for their experiments.

The CycleNet dataset is a graph representation learning dataset that uses the CycleNet framework to encode cycle information in graphs.

PCQM4M is a quantum chemistry dataset originally curated under the PubChemQC project.

Open Graph Benchmark: Datasets for machine learning on graphs.

The dataset used in the paper is a graph dataset, where each node represents a person and each edge represents a connection between two people. The dataset is used to evaluate...

The dataset used in the paper is a graph dataset, where each node represents a person and each edge represents a connection between two people. The dataset is used to evaluate...

The IMDB-Binary dataset is a graph neural network dataset.

The Proteins dataset is a graph neural network dataset.

Graph4GUI: Graph Neural Networks for Representing Graphical User Interfaces

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