Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning

IEEE Signal Processing Society via YouTube

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore subgraph-based networks for graph learning in this IEEE Signal Processing Society webinar presented by Haggai Maron from NVIDIA Research. Delve into the concepts of explicit power, color refinement, and exclusivity in graph learning. Understand the importance of equivariance and its benefits in neural networks. Examine the DSSA architecture, its theoretical and experimental analysis, and its application to large graphs. Learn about node-based policies, tensors, and other approaches in graph learning. Gain insights into the Sun architecture and its experimental results. Conclude with a summary and Q&A session on expressive, efficient, and domain-independent graph learning techniques.

Syllabus

Introduction
Learning on graphs
Explicit power
Color refinement
Limitless exclusivity
Why exclusivity matters
Goal
Recipe
What is a suitable neural network
Equivariance
Equivariant
Benefits
Two kinds of symmetry
DSS
Architecture
Large graphs
Theoretical analysis
Experimental analysis
Evaliant graph networks
Nodebased policies
Tensors
Intuition
Other approaches
Sun architecture
Brain
Experiment
Summary
Conclusion
Questions

Taught by

IEEE Signal Processing Society

Reviews

Start your review of Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.