Abhik Sarkar's avatar

Graph Theory & Neural Networks

Explore interactive visualizations of graph algorithms, neural networks on graphs, and fundamental graph theory concepts. From basic centrality measures to advanced graph neural networks.

Graph Convolutional Networks (GCN)

Message passing, spectral theory, and neighborhood aggregation in GCNs

Explore

Graph Attention Networks (GAT)

Adaptive attention-based aggregation with multi-head architectures

Explore

Graph Pooling Methods

Hierarchical pooling, DiffPool, SAGPool, and readout operations

Explore

Graph Embeddings

Node2Vec, DeepWalk, random walks, and skip-gram training

Explore

Graph Centrality & Metrics

Centrality measures, shortest paths, clustering coefficients

Explore

What You'll Learn

Fundamentals

  • • Graph structure and representations
  • • Shortest paths and hop distances
  • • Centrality measures and importance
  • • Clustering and community detection

Advanced Topics

  • • Graph neural network architectures
  • • Attention mechanisms on graphs
  • • Graph embeddings and representation learning
  • • Hierarchical pooling and coarsening
All visualizations are interactive and include implementation examples in PyTorch.
Mastodon