Graph machine learning
Graph machine learning comprises machine-learning methods that learn representations, predictions, or patterns from graph-structured data and relationships.
Optimization Algorithms: AI techniques for design, planning, and control problems
Graph machine learning is machine learning on graph-structured data that models relationships among entities as well as entity attributes.
- How it is used
- Models relationships in graph-structured data, including relationships and constraints relevant to combinatorial optimization.
- How deep it goes
- Moves from graph construction and embedding to GCN intuition and a PyTorch Geometric training example, without a formal proof.
- Examples
- Uses a soccer-player graph, road-segment ETA prediction, and a Cora node-embedding implementation.
- What you can do after
- Apply it via NetworkX and PyTorch Geometric to construct a graph and experiment with a GCN on node data.
Graph Algorithms for Data Science
Graph machine learning is machine learning that represents data and their relationships as a graph and exploits graph structure during modeling.
- How it is used
- Uses relationships and network position to add context to machine-learning workflows.
- How deep it goes
- Explains workflow applications and graph-derived features, while stopping short of detailed machine-learning implementation.
- Examples
- Uses social-platform graphs, influential nodes, community structure, and future-link prediction as concrete examples.
- What you can do after
- Evaluate graph-shaped machine-learning problems and select node, clustering, or link-prediction workflows using network context.
Read how Graph Algorithms for Data Science explains graph machine learning →
Graph Neural Networks in Action
Graph-based learning applies machine learning to data represented as a graph and learns from its structural relationships.
- How it is used
- Applies machine learning to relational data for representation learning, prediction, classification, and graph analysis.
- How deep it goes
- Defines graph-learning families, embeddings, GNN message passing, and preprocessing workflows without deriving their mathematics.
- Examples
- Uses Titanic-derived data, social networks, biological networks, and a recruiting-firm candidate graph.
- What you can do after
- Apply graph workflows with NetworkX and PyTorch Geometric, from raw data conversion through graph preparation and GNN training.
Read how Graph Neural Networks in Action explains graph machine learning →
Related concepts
- machine learningkind of · Machine learning is a field of computational methods in which systems learn patterns or relationships from data to make predictions, decisions, or other outputs.
- graph neural networkused by · A graph neural network is a neural-network model that learns representations or predictions from graph-structured data by combining information from connected entities.
- embeddingproduces · A numerical vector representation of an item or input that encodes features or relationships useful for computational tasks.
- deep learningkind of · Deep learning is a machine-learning approach that uses neural networks with multiple computational layers to learn representations from data.
- permutation invarianceuses · Permutation invariance is the property that a computation’s result remains unchanged when equivalent input elements are reordered.
- local neighborhooduses · A local neighborhood is a set of elements considered near a specified element according to a defined spatial, topological, distance-based, or relational criterion.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.