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

Sampling is a critical operation in Graph Neural Network (GNN) training that helps reduce the cost. Previous literature has explored improving sampling algorithms via mathematical and statistical methods. However, there is a gap between sampling algorithms and hardware. Without consideration of hard...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-06
Hauptverfasser:	Liu, Xin, Yan, Mingyu, Song, Shuhan, Lv, Zhengyang, Li, Wenming, Sun, Guangyu, Ye, Xiaochun, Fan, Dongrui
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Algorithms Datasets Graph neural networks Graph theory Hardware Model accuracy Sampling Statistical methods Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!