Advanced Deep Learning
- Course Introduction
- Overview of Deep Network Development Trends and Their Future Outlook
- Graph Networks: Machine Learning on Graphs, Node Embedding
- Graph Convolutional Networks, Graph Attention Networks
- Graph Network Design, Simplification of Graph Convolutional Networks
- Hierarchical Graph Representation Learning
- Heterogeneous Graphs and Heterogeneous Graph Transformer Networks
- Knowledge Graphs and Reasoning over Knowledge Graphs
- Fast Subgraph Matching and Scaling to Large Graphs
- Deep Generative Models for Graphs
- Graph Transformer Networks, Position-Aware and Identity-Aware Graph Networks
- Generative Models: Concepts and Applications, Variational Autoencoders, Normalizing Flow Models
- Basic Generative Adversarial Networks (GANs), Wasserstein GAN, Conditional GAN, Progressive Growing GAN, StyleGAN, CycleGAN
- Diffusion Models: Mathematical Foundations, Training, and Applications
- Selected Topics