Graph Neural Network

Graph Neural Networks (GNNs) are a class of machine learning models designed to analyze and learn from data represented as graphs, focusing on capturing relationships between nodes and their impact on downstream tasks like node classification and link prediction. Current research emphasizes improving GNN performance by addressing limitations such as oversmoothing and oversquashing through architectural innovations (e.g., incorporating residual connections, Cayley graph propagation) and novel training techniques (e.g., contrastive learning, Laplacian regularization). GNNs are proving valuable across diverse fields, including social network analysis, drug discovery, and financial modeling, offering powerful tools for analyzing complex relational data where traditional methods fall short.

Papers

November 29, 2023

November 28, 2023

November 27, 2023

Soil Organic Carbon Estimation from Climate-related Features with Graph Neural Network
Weiying Zhao, Natalia Efremova
Graph Neural Network GNN Model Soil Organic Carbon

November 26, 2023

Solve Large-scale Unit Commitment Problems by Physics-informed Graph Learning
Jingtao Qin, Nanpeng Yu
Graph Neural Network Mixed Integer Graph Neural Network Model Unit Commitment

November 25, 2023

November 24, 2023

November 22, 2023

November 21, 2023

Unsupervised Graph Attention Autoencoder for Attributed Networks using K-means Loss
Abdelfateh Bekkair, Slimane Bellaouar, Slimane Oulad-Naoui
Graph Neural Network Community Detection Graph Attention Community Structure Social Network Analysis Attributed Network

November 20, 2023

Graph Neural Network

Papers

The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation

How does spatial structure affect psychological restoration? A method based on Graph Neural Networks and Street View Imagery

Attentional Graph Neural Networks for Robust Massive Network Localization

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs

Soil Organic Carbon Estimation from Climate-related Features with Graph Neural Network

Solve Large-scale Unit Commitment Problems by Physics-informed Graph Learning

Exploring Causal Learning through Graph Neural Networks: An In-depth Review

Robust Graph Neural Networks via Unbiased Aggregation

Advancing Fluid-Based Thermal Management Systems Design: Leveraging Graph Neural Networks for Graph Regression and Efficient Enumeration Reduction

Effective Structural Encodings via Local Curvature Profiles

AdaMedGraph: Adaboosting Graph Neural Networks for Personalized Medicine

Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI

Benchmarking Toxic Molecule Classification using Graph Neural Networks and Few Shot Learning

Comprehensive Evaluation of GNN Training Systems: A Data Management Perspective

Hard Label Black Box Node Injection Attack on Graph Neural Networks

Unsupervised Graph Attention Autoencoder for Attributed Networks using K-means Loss

AMES: A Differentiable Embedding Space Selection Framework for Latent Graph Inference

Robust Tumor Segmentation with Hyperspectral Imaging and Graph Neural Networks

Unveiling the Unseen Potential of Graph Learning through MLPs: Effective Graph Learners Using Propagation-Embracing MLPs

CSGNN: Conquering Noisy Node labels via Dynamic Class-wise Selection