Graph Attention Networks (GAT)
Adaptive attention-based aggregation for graph neural networks - multi-head attention, learned weights, and interpretable graph learning
No direct links0 refs
🔗
Graph Theory & Neural Networks
Graph algorithms, neural networks on graphs, and fundamental graph theory concepts with interactive visualizations.
5
Concepts
All Graph Theory & Neural Networks Concepts
Graph Centrality & Metrics
Understanding node importance through centrality measures, shortest paths, hop distances, clustering coefficients, and fundamental graph metrics
graph-centralitygraph-metricsshortest-pathsclustering-coefficientdegree-centralitybetweennesscloseness
No direct links0 refs
Graph Convolutional Networks (GCN)
Learn Graph Convolutional Networks (GCN) with spectral theory, message passing, and node classification for geometric deep learning.
GCNgraph-neural-networksmessage-passingspectral-methodsnode-classificationgraph-learninggeometric-deep-learning
No direct links0 refs
Graph Embeddings
Learning low-dimensional vector representations of graphs through random walks, DeepWalk, Node2Vec, and skip-gram models
No direct links0 refs
Graph Pooling Methods
Hierarchical graph coarsening techniques - TopK, SAGPool, DiffPool, and readout operations for graph-level representations
No direct links0 refs