.png){kind=icon}
返回
SUGAR: Efficient Subgraph-Level Training via Resource-Aware Graph Partitioning
.png){kind=icon}
OA
AI
DOI：10.1109/TC.2023.3288755.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Nevertheless, resource-efficient GNN learning is a rarely explored topic despite its many benefits for edge computing and Internet of Things (IoT) applications. To improve this state of affairs, this work proposes efficient subgraph-level training via resource-aware graph partitioning (SUGAR). SUGAR first partitions the initial graph into a set of disjoint subgraphs and then performs local training at the subgraph-level We provide a theoretical analysis and conduct extensive experiments on five graph benchmarks to verify its efficacy in practice. Our results across five different hardware platforms demonstrate great runtime speedup and memory reduction of SUGAR on large-scale graphs. We believe SUGAR opens a new research direction towards developing GNN methods that are resource-efficient, hence suitable for IoT deployment.
Keyword:
Graph neural networks
resource-efficient learning
edge computing
期刊
IF:
3.8
论文数:
5.4K
被引数:
9.8K
机构
引用论文
.png){kind=icon}
Weight and age at puberty in female and male mice of strains selected for large and small body size
OAAI
OAAI分享收藏分享收藏
查看更多内容