CS224W - Lecture 1.1 - Why Graphs
Aug 31, 2022
# Timestamped Notes
# Why Graphs?
- Graphs are a general language for describing and analyzing entities with relations/interactions.
- Many types of data can be represented as graphs:
- Event Graphs
- Computer Networks
- Disease Pathways
- Food Webs
- Particle Networks
- Underground Networks
- Social Networks
- Economic Networks
- Communication Networks
- Citation Networks
- Network of Neurons
- Knowledge Graphs
- Regulatory Networks
- Scene Graphs
- Code Graphs
- 3D Shapes.
# Types of Networks and Graphs
- Networks or Natural Graphs
- Underlying domains can naturally be represented as graphs.
- Social Networks
- Communication and transactions
- Brain Connections
- Similarity networks
- Relational structures
- Sometimes, the distinction between networks and graphs is blurred.
- [?] How do we take advantage of relational structure for better prediction?
- Complex domains have rich relational structure, which can be represented as a relational graph.
- By explicitly modeling relationships, we achieve better performance.
- Modern deep learning toolbox is designed for simple sequences and grids.
- Such as images, audio, video, etc.
- Graph/Networks are much harder to process because they are more complex.
- They have arbitrary size and complex topological structure (i.e., no spatial locality like grids).
- No fixed node ordering or reference point.
- Often dynamic and have multimodal features.
- Graphs are the new frontier of deep learning.
# Representational Learning
- Representational learning allows us to automatically learn the features. We don’t have to perform manual feature engineering.
- To perform Representational Learning, we can map nodes to $d$-dimensional embeddings such that similar nodes in the network are embedded close together.
# Course Outline
- Traditional methods
- Methods for node embeddings
- Graph Neural Networks
- Knowledge graphs and reasoning
- Deep generative models for graphs
- Applications to Biomedicine, Science, Industry