Graph ML — Roadmap

1. Graph ML Fundamentals

• Graph representation: nodes, edges, adjacency
• Task taxonomy: node classification, link prediction, graph classification
• GCN, GraphSAGE, GAT (see Advanced Architectures), GIN
• Graph embeddings: node2vec, DeepWalk
• Knowledge graphs
• Graph RAG (see RAG — GraphRAG)

Next: AI for Science — where graph representations (molecules, protein structures) become one of several scientific-domain applications of ML.