-
Haar Graph Pooling
Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which... -
Pitfalls of graph neural network evaluation
Pitfalls of graph neural network evaluation -
Inductive Matrix Completion Using Graph Autoencoder
Matrix completion has been formulated as the link prediction problem on a bipartite user-item graph in recent GNN-based matrix completion methods. -
Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation
A concept-aware denoising graph neural network for micro-video recommendation -
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,... -
Graph Neural Networks
Graph Neural Networks (GNNs) have emerged as powerful tools for learning graph-structured data in various domains. -
Synthetic Graphs
The dataset used in the paper is a synthetic graph generated using the Stochastic Block Model (SBM) with 10 classes and 100 nodes per class. -
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. -
PCQM4M and PCQM4Mv2
PCQM4M and PCQM4Mv2 are large-scale molecular graph datasets. -
Benchmarking graph neural networks
Benchmarking graph neural networks. -
Meta-GraphSHS Dataset
This dataset is used to evaluate the performance of the proposed Meta-GraphSHS model for discovering structural hole spanners in diverse networks. -
GraphSHS Dataset
This dataset is used to evaluate the performance of the proposed GraphSHS model for discovering structural hole spanners in large-scale and diverse networks. -
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... -
Discrete-Valued Neural Communication
The dataset used in the paper is a visual reasoning task using Graph Neural Networks (GNNs) and Recurrent Independent Mechanisms (RIMs). The dataset consists of 8 Atari games... -
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...
