01Module 13 - Graph Neural NetworksMaster graph neural networks for drug discovery, fraud detection, and recommendations. GCN, GAT, GraphSAGE, MPNN, and knowledge graph embeddings with PyTorch Geometric.02Why Graphs for MLWhen tabular data fails - graph formalism, adjacency matrix, Laplacian, graph types, real-world datasets, the Weisfeiler-Lehman test, and why CNNs cannot handle graph-structured data.03Graph Representation for MLNode embeddings from shallow methods to GNNs - DeepWalk, Node2Vec, LINE, spectral embeddings, manual features, and their fundamental limitations. How to featurize nodes, edges, and graphs.04Graph Convolutional NetworksGCN derivation from spectral graph theory to efficient spatial message passing. Symmetric normalization, renormalization trick, over-smoothing, and training on Cora with PyG.05Graph Attention NetworksGAT - learning which neighbors matter via attention over graph edges. Multi-head attention, GATv2's dynamic attention, heterophilic graphs, and training on Cora with PyTorch Geometric.06GraphSAGE and Inductive LearningGraphSAGE - sample and aggregate for inductive GNNs that generalize to unseen nodes. Neighbor sampling, mini-batch training, unsupervised learning, and PinSage for billion-scale recommendations.07Message Passing Neural NetworksMPNN - the unified framework showing GCN, GraphSAGE, and GAT are special cases of a single message-passing paradigm with a fundamental 1-WL expressivity ceiling.08GNNs for Recommender SystemsHow LightGCN, PinSage, and NGCF use graph neural networks on user-item interaction graphs to capture multi-hop collaborative filtering signals at billion-scale.09Knowledge Graph EmbeddingsTransE, RotatE, CompGCN - embedding entities and relations in vector spaces to predict missing facts in knowledge graphs, enabling AI systems to reason about structured world knowledge.
