Seonglae ChoGraph neural network for Graph Data
An artificial neural network designed to process data that can be represented as graphs, where existing neural network architectures can be interpreted as GNNs operating on appropriately defined graphs.
Academia is trying to find a token-like material to represent every vector format in the same latent space using nodes and edges
GNN Models
GNN Notion
Understanding GNNs
Similar to the brain Neuron architecture with no limit to the volume, might be better volume simulating regularization for optimization.
A Gentle Introduction to Graph Neural Networks
What components are needed for building learning algorithms that leverage the structure and properties of graphs?
https://distill.pub/2021/gnn-intro/
Understanding Convolutions on Graphs
Understanding the building blocks and design choices of graph neural networks.
https://distill.pub/2021/understanding-gnns/
Classification
Learnable Structural Semantic Readout for Graph Classification
With the great success of deep learning in various domains, graph neural networks (GNNs) also become a dominant approach to graph classification. By the help of a global readout operation that...
https://arxiv.org/abs/2111.11523
Geometric GNN
arxiv.org
https://arxiv.org/pdf/2312.07511.pdf