当前位置: X-MOL 学术arXiv.cs.PF › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Architectural Implications of Graph Neural Networks
arXiv - CS - Performance Pub Date : 2020-09-02 , DOI: arxiv-2009.00804
Zhihui Zhang, Jingwen Leng, Lingxiao Ma, Youshan Miao, Chao Li, Minyi Guo

Graph neural networks (GNN) represent an emerging line of deep learning models that operate on graph structures. It is becoming more and more popular due to its high accuracy achieved in many graph-related tasks. However, GNN is not as well understood in the system and architecture community as its counterparts such as multi-layer perceptrons and convolutional neural networks. This work tries to introduce the GNN to our community. In contrast to prior work that only presents characterizations of GCNs, our work covers a large portion of the varieties for GNN workloads based on a general GNN description framework. By constructing the models on top of two widely-used libraries, we characterize the GNN computation at inference stage concerning general-purpose and application-specific architectures and hope our work can foster more system and architecture research for GNNs.

中文翻译:

图神经网络的架构含义

图神经网络 (GNN) 代表了对图结构进行操作的一系列新兴深度学习模型。由于其在许多与图相关的任务中实现的高精度,它变得越来越流行。然而,GNN 在系统和架构社区中的理解不如多层感知器和卷积神经网络等对应物好。这项工作试图将 GNN 介绍给我们的社区。与之前仅呈现 GCN 特征的工作相比,我们的工作涵盖了基于通用 GNN 描述框架的 GNN 工作负载的大部分种类。通过在两个广泛使用的库之上构建模型,
更新日期:2020-09-03
down
wechat
bug