01Module 09 - Graph Theory for ML EngineeringOverview of graph theory for ML - graph fundamentals, algorithms, spectral methods, network models, and graph neural networks. Connects to GNNs, knowledge graphs, social networks, and molecular ML.02Graph Fundamentals - Vertices, Edges, Paths, and Graph Types in MLDeep engineering guide to graph theory fundamentals - vertices, edges, directed vs undirected, weighted graphs, paths, cycles, connectivity, and their roles in knowledge graphs, citation networks, and molecular ML.03Graph Representations - Adjacency Matrix, Edge List, and ML TradeoffsEngineering guide to graph representation formats - adjacency matrix, adjacency list, edge list, incidence matrix, and memory/compute trade-offs for GNN workloads in PyTorch Geometric and DGL.04Graph Algorithms - BFS, DFS, Dijkstra, PageRank, and ML Feature EngineeringEngineering guide to core graph algorithms - BFS, DFS, Dijkstra's shortest path, topological sort, minimum spanning tree, PageRank, and how they enable graph-based feature engineering for ML.05Spectral Graph Theory - Graph Laplacian, Eigenvalues, and Spectral ClusteringEngineering guide to spectral graph theory - graph Laplacian, spectral decomposition, graph Fourier transform, spectral clustering, and the connection to Graph Convolutional Networks.06Random Graphs and Network Models - Erdős-Rényi, Scale-Free, and Synthetic DataEngineering guide to random graph models - Erdős-Rényi model, Barabási-Albert scale-free networks, small-world networks, degree distributions, and generating synthetic graph data for ML.07Graph Theory for GNNs - Message Passing, Expressiveness, and Over-SmoothingEngineering guide to the graph-theoretic foundations of GNNs - message passing framework, GCN/GraphSAGE/GAT, Weisfeiler-Leman expressive power, over-smoothing, and PyTorch Geometric implementation.
