COIN: Communication-Aware In-Memory Acceleration for Graph Convolutional Networks

Graph convolutional networks (GCNs) have shown remarkable learning capabilities when processing graph-structured data found inherently in many application areas. GCNs distribute the outputs of neural networks embedded in each vertex over multiple iterations to take advantage of the relations capture...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-05
Hauptverfasser:	Mandal, Sumit K, Krishnan, Gokul, A Alper Goksoy, Gopikrishnan Ravindran Nair, Cao, Yu, Ogras, Umit Y
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Communication Computation Computer memory Computer Science - Hardware Architecture Computer Science - Learning Energy consumption Hardware Structured data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!