-
FunQG: Molecular Representation Learning Via Quotient Graphs
The FunQG framework is a novel molecular graph coarsening framework for more efficient learning of molecular representations. -
Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities
Graph pooling is an essential component of the architecture for many graph-level tasks, such as graph classification and graph generation. -
ogbn-products
Graph Neural Networks (GNNs) have become a popular approach for various applications, ranging from social network analysis to modeling chemical properties of molecules. -
Tangent Bundle Neural Networks
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... -
RobustMat: Neural Diffusion for Street Landmark Patch Matching under Challeng...
For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing. In various computer... -
Open Graph Benchmark
Open Graph Benchmark (OGB) dataset contains many large-scale benchmark datasets. -
Benchmark: Datasets for Machine Learning on Graphs
Benchmarking graph neural networks. -
SoGCN: Second-Order Graph Convolutional 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... -
UniAug: A Universal Graph Structure Augmentor
Graph structure augmentation pipeline UniAug to leverage the increasing scale of graph data. -
Learning Latent Interactions for Event classification via Graph Neural Network...
The proposed method learns latent interaction graph jointly with feature engineering and event identification model, thus improving the accuracy of the graph learning and... -
Progressive Graph Convolutional Networks for Spatial-Temporal Traffic Forecas...
The complex spatial-temporal correlations in traffic data make the traffic forecasting problem challenging. The proposed model captures the time-varying spatial correlations by... -
Universal Polynomial Bases for Spectral Graph Neural Networks
The dataset used in the paper is a collection of real-world datasets with varying heterophily degrees, including Cora, Citeseer, Pubmed, Actor, Chameleon, Squirrel, Penn94,... -
Amazon Photos
The dataset used in the paper to evaluate the influence of graph elements on the parameter changes of GCNs without needing to retrain the GCNs. -
Amazon Computers
The dataset used in the paper to evaluate the influence of graph elements on the parameter changes of GCNs without needing to retrain the GCNs. -
ogbn-arxiv
The ogbn-arxiv dataset is a citation network dataset, which is a directed graph, denoting the citation network between all Computer Science (CS) arXiv papers extracted from the... -
Synthetic Graph Dataset
A synthetic dataset of 200 graphs with 5 nodes each, where nodes were randomly placed within a designated area of operation using a random point configuration of the Euclidean...
