.png){kind=icon}
返回
Distributed Optimization of Graph Convolutional Network Using Subgraph Variance
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2023.3243904.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, distributed graph convolutional networks (GCNs) training frameworks have achieved great success in learning the representation of graph-structured data with large sizes. However, existing distributed GCN training frameworks require enormous communication costs since a multitude of dependent graph data need to be transmitted from other processors. To address this issue, we propose a graph augmentation-based distributed GCN framework (GAD). In particular, GAD has two main components: GAD-Partition and GAD-Optimizer. We first propose an augmentation-based graph partition (GAD-Partition) that can divide the input graph into augmented subgraphs to reduce communication by selecting and storing as few significant vertices of other processors as possible. To further speed up distributed GCN training and improve the quality of the training result, we design a subgraph variance-based importance calculation formula and propose a novel weighted global consensus method, collectively referred to as GAD-Optimizer. This optimizer adaptively adjusts the importance of subgraphs to reduce the effect of extra variance introduced by GAD-Partition on distributed GCN training. Extensive exper-iments on four large-scale real-world datasets demonstrate that our framework significantly reduces the communication overhead (asymptotic to 50%), improves the convergence speed (asymptotic to 2x) of distributed GCN training, and obtains a slight gain in accuracy (asymptotic to 0.45%) based on minimal redundancy compared to the state-of-the-art methods.
Keyword:
Communicate reduction
distribution optimize
graph augmentation
graph convolutional network (GCN)
sub-graph variance
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Conjugated heat transfer and temperature distributions in a gas turbine combustion liner under base-load operation基本负荷运行下燃气轮机燃烧衬里中的共轭传热和温度分布
PREAI
分享收藏
Effective Deep Attributed Network Representation Learning With Topology Adapted Smoothing具有拓扑自适应平滑的有效深度属性网络表示学习
PREAI
分享收藏Graph classification based on structural features of significant nodes and spatial convolutional neural networks基于显著节点结构特征和空间卷积神经网络的图分类.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏
查看更多内容