Hardware Acceleration of Sampling Algorithms in Sample and Aggregate Graph Neural Networks

09/07/2022
by   Yuchen Gui, et al.
0

Sampling is an important process in many GNN structures in order to train larger datasets with a smaller computational complexity. However, compared to other processes in GNN (such as aggregate, backward propagation), the sampling process still costs tremendous time, which limits the speed of training. To reduce the time of sampling, hardware acceleration is an ideal choice. However, state of the art GNN acceleration proposal did not specify how to accelerate the sampling process. What's more, directly accelerating traditional sampling algorithms will make the structure of the accelerator very complicated. In this work, we made two contributions: (1) Proposed a new neighbor sampler: CONCAT Sampler, which can be easily accelerated on hardware level while guaranteeing the test accuracy. (2) Designed a CONCAT-sampler-accelerator based on FPGA, with which the neighbor sampling process boosted to about 300-1000 times faster compared to the sampling process without it.

READ FULL TEXT

page 5

page 6

research
03/02/2023

HitGNN: High-throughput GNN Training Framework on CPU+Multi-FPGA Heterogeneous Platform

As the size of real-world graphs increases, training Graph Neural Networ...
research
08/26/2021

GNNSampler: Bridging the Gap between Sampling Algorithms of GNN and Hardware

Sampling is a critical operation in the training of Graph Neural Network...
research
12/22/2021

HP-GNN: Generating High Throughput GNN Training Implementation on CPU-FPGA Heterogeneous Platform

Graph Neural Networks (GNNs) have shown great success in many applicatio...
research
03/19/2021

GNNerator: A Hardware/Software Framework for Accelerating Graph Neural Networks

Graph Neural Networks (GNNs) use a fully-connected layer to extract feat...
research
03/24/2023

IMA-GNN: In-Memory Acceleration of Centralized and Decentralized Graph Neural Networks at the Edge

In this paper, we propose IMA-GNN as an In-Memory Accelerator for centra...
research
03/01/2021

A Biased Graph Neural Network Sampler with Near-Optimal Regret

Graph neural networks (GNN) have recently emerged as a vehicle for apply...
research
01/27/2023

TrojanSAINT: Gate-Level Netlist Sampling-Based Inductive Learning for Hardware Trojan Detection

We propose TrojanSAINT, a graph neural network (GNN)-based hardware Troj...

Please sign up or login with your details

Forgot password? Click here to reset