GNN Transformation Framework for Improving Efficiency and Scalability

07/25/2022
by   Seiji Maekawa, et al.
0

We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs. The advantages of our framework are two-fold; 1) it transforms various non-scalable GNNs to scale well to large-scale graphs by separating local feature aggregation from weight learning in their graph convolution, 2) it efficiently executes precomputation on GPU for large-scale graphs by decomposing their edges into small disjoint and balanced sets. Through extensive experiments with large-scale graphs, we demonstrate that the transformed GNNs run faster in training time than existing GNNs while achieving competitive accuracy to the state-of-the-art GNNs. Consequently, our transformation framework provides simple and efficient baselines for future research on scalable GNNs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/02/2022

Rethinking Efficiency and Redundancy in Training Large-scale Graphs

Large-scale graphs are ubiquitous in real-world scenarios and can be tra...
research
10/27/2021

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

Many widely used datasets for graph machine learning tasks have generall...
research
10/14/2022

A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking

Large-scale graph training is a notoriously challenging problem for grap...
research
01/23/2022

Hardware/Software Co-Programmable Framework for Computational SSDs to Accelerate Deep Learning Service on Large-Scale Graphs

Graph neural networks (GNNs) process large-scale graphs consisting of a ...
research
07/18/2018

Evolving Large-Scale Data Stream Analytics based on Scalable PANFIS

Many distributed machine learning frameworks have recently been built to...
research
03/12/2022

GRAND+: Scalable Graph Random Neural Networks

Graph neural networks (GNNs) have been widely adopted for semi-supervise...

Please sign up or login with your details

Forgot password? Click here to reset