| 01 |
Course Orientation |
Learning Objectives, Course Schedule, Introduction to Graph Machine Learning |
pdf |
| 02 |
Introduction to Graphs |
Graph Notation, Types, and Characteristics |
pdf |
| 03 |
Graph Representation |
Nodes, Edges, Structures, Data Store Objects |
pdf |
| 04 |
Node Embedding |
Embedding Space, Random Walks, DeepWalk, Node2Vec |
pdf |
| 05 |
Permutation Equivariance & Invariance |
Canonical Graph, Permutation Equivariance & Invariance in Graphs |
pdf |
| 06 |
Graph Convolution Networks |
GCN Formulation, Training GCN, Inductive Capabilities |
pdf |
| 07 |
Message Passing Neural Networks |
Unified Message Passing, GraphSAGE, Graph Attention Networks |
pdf |
| 08 |
Mid-term Exam |
Research-centric Presentation & Idea Formulation |
N/A |
| 09 |
Practical Design of GNNs |
Batch Norm, Dropout, Over-smoothing, Skip Connections, Augmentation, Manipulation |
pdf |
| 10 |
GNN Training & Evaluation |
Node-, Edge-, Graph-level Prediction, Loss, Transductive vs. Inductive Learning, Split Technologies |
pdf |