Large-Scale Graph Neural Networks: 

The Past and New Frontiers

 

Abstract

Graph Neural Networks (GNNs) have gained significant attention in recent years due to their ability to model complex relationships between entities in graph-structured data such as social networks, protein structures, and knowledge graphs. However, due to the size of real-world industrial graphs and the special architecture of GNNs, it is a long-lasting challenge for engineers and researchers to deploy GNNs on large-scale graphs, which significantly limits their applications in real-world applications. In this tutorial, we will cover the fundamental scalability challenges of GNNs, frontiers of large- scale GNNs including classic approaches and some newly emerging techniques, the evaluation and comparison of scalable GNNs, and their large-scale real-world applications. Overall, this tutorial aims to provide a systematic and comprehensive understanding of the challenges and state-of-the-art techniques for scaling GNNs. The summary and discussion on future directions will inspire engineers and researchers to explore new ideas and developments in this rapidly evolving field.

 

 

Outline

1. Introduction of GNNs (25 minutes)


(a) Foundations of GNNs

(b) Applications of GNNs

(c) Scalability Challenges of Large-Scale GNNs

2. Classic Approaches for Scaling GNNs (60 minutes)

 (a) Sampling Methods  

 (b) Decoupling Methods

(c) Distributed Methods


Break: 5 minutes

3. Emerging Techniques for Scaling GNNs (60 minutes)


Training:


(a)  Lazy Propagation

(b)  Alternating Training

(c)  GNN Pre-training


Inferencing:

Cross-model Distillation


Data:

(a)  Graph Condensation

(b)  Subgraph Sketching

(c)  Tabularization

4. Evaluation, Comparison and Applications (20 minutes) 


5. Summary and Future Directions (10 minutes)

Tutorial Slides

KDD2023_tutorial.pdf

Photo Gallery