69 datasets found

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

The CORD-19 dataset contains academic journal articles relating to a variety of coronaviruses and related viral infections, not only COVID-19, sourced from PubMed Central (PMC),...

The dataset used in the paper is a collection of real-world benchmark datasets for node classification.

Bipartite graphs with capacities and weights, used for training and evaluation of neural bipartite matching.

The dataset used in the paper is a citation network, specifically Cora, CiteSeer, PubMed, Coauthor-CS, and Coauthor-Physics.

The dataset used in this paper is the Polblogs dataset, which contains 1,222 blogs.

The dataset is used to test the performance of Tangent Bundle Neural Networks on three tasks: denoising of a tangent vector field on the torus, reconstruction from partial...

The dataset used in the paper is a graph neural network (GNN) dataset, where the goal is to learn a GNN with one hidden layer for node information convolution.

For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing. In various computer...

This paper introduces STAR, a framework for spatio-temporal crowd trajectory prediction with only attention mechanisms.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors evaluate CatFlow on a graph generation task.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors evaluate CatFlow on three sets of experiments: abstract graph generation,...

Reliable fault detection is an essential requirement for safe and efficient operation of complex mechanical systems in various industrial applications.

Open Graph Benchmark (OGB) dataset contains many large-scale benchmark datasets.

Benchmarking graph neural networks.

Graph Convolutional Networks (GCNs) with multi-hop aggregation is more expressive than one-hop GCN but suffers from higher model complexity. Finding the shortest aggregation...

The Coauthor Physics dataset is a co-authorship graph extracted from the Microsoft Academic Graph, with a focus on Physics research.

This dataset contains graph-structured data and its corresponding features.

Graph structure augmentation pipeline UniAug to leverage the increasing scale of graph data.

UniSG: A unified entity-component-system in a scenegraph architecture, designed to address the demands of scientific, visual, and neural computing applications.