liveBook · Manning

Geometric deep learning

As explained in Optimization Algorithms: AI techniques for design, planning, and control problems

Geometric deep learning is a family of deep-learning methods designed to operate on data with geometric or relational structure.

Geometric deep learning (GDL) extends deep neural models to data whose meaning depends on geometric or relational structure rather than regular Euclidean layout. It supports graphs, point clouds, molecules, and manifolds, making relationships between entities part of the learning problem. section 11.10 section 11.3

GDL is useful when structure carries information that ordinary distance does not capture:

  • Treats nodes and edges as the important structure in graphs, where neighborhoods and connections may vary between nodes. section 11.3
  • Supports graph machine-learning tasks such as node classification, link prediction, and community detection. section 11.3
  • Uses graph embedding or representation learning to convert discrete, high-dimensional graph data into lower-dimensional continuous representations. section 11.10 section 11.3

Turning player records into a graph

A soccer dataset can represent players, clubs, and nationalities as nodes. Add a plays_for edge from each player to a club and a belongs_to edge from each player to a nationality. The resulting graph exposes relationships that a flat table does not represent directly, and it can be inspected with a network layout. section 11.3

Listing 11.1 Converting tabular data to a graph
import pandas as pd
import networkx as nx
import matplotlib.pyplot as plt
  
data={'Player':['L. Messi','R. Lewandowski','C. Ronaldo','Neymar Jr','K. 
 Mbappé','E.Haaland','H. Kane','Luka Modrić','L. Goretzka','M. Salah'],
    'Age':[36,34,38,22,24,35,29,37,28,31],
    'Nationality':['Argentina','Poland','Portugal','Brazil','France','Norway',
    'England','Croatia','Germany','Egypt'],
    'Club':['Inter Miami','Barcelona','Al-Nassr','Al-Hilal ','PSG','Manchester
    City','Tottenham Hotspur','Real Madrid','Bayern Munich','Liverpool'],
    'League':['Major League Soccer ','Spain Primera Division','Saudi Arabia
 League','Saudi Arabia League','French Ligue 1','English Premier
 League','English Premier League','Spain Primera Division','German 1.
 Bundesliga','English Premier League']}
df=pd.DataFrame.from_dict(data)

Use the listing to create a graph from tabular player data with pandas, NetworkX, and Matplotlib before applying graph-learning methods. section 11.3

How Optimization Algorithms: AI techniques for design, planning, and control problems covers it

How deep it goes
Defines the structural distinction and introduces embeddings, but stops short of neural architectures, training procedures, and model internals.
Examples
Uses soccer players, clubs, nationalities, tabular records, graph edges, and network visualizations as concrete examples.
What you can do after
Build graph-structured inputs from tabular data with pandas and NetworkX for downstream graph-learning tasks.
How it connects
Connects deep learning with graph theory, graph machine learning, graph embedding, node classification, link prediction, and community detection.
Cover of Optimization Algorithms: AI techniques for design, planning, and control problems
liveBookmanning.com
Read Optimization Algorithms: AI techniques for design, planning, and control problems on liveBook Get the book at manning.com

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Optimization Algorithms: AI techniques for design, planning, and control problems. The section links point to the parts of the book it draws on.