GraNNDis: Fast Distributed Graph Neural Network Training Framework for Multi-Server Clusters

Graph neural networks (GNNs) are one of the rapidly growing fields within deep learning. While many distributed GNN training frameworks have been proposed to increase the training throughput, they face three limitations when applied to multi-server clusters. 1) They suffer from an inter-server commu...

Celý popis

Podrobná bibliografie

Vydáno v:	2024 33rd International Conference on Parallel Architectures and Compilation Techniques (PACT) s. 91 - 107
Hlavní autoři:	Song, Jaeyong, Jang, Hongsun, Lim, Hunseong, Jung, Jaewon, Kim, Youngsok, Lee, Jinho
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	ACM 13.10.2024
Témata:	Distributed Graph Neural Network Training Distributed Systems Graph Neural Network Training Graph neural networks Knowledge engineering Parallel architectures Redundancy Sampling methods Scalability Servers Systems for Deep Learning Throughput Training
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!