arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.00804cs.ARcs.LGcs.PF
收藏

图神经网络的体系结构含义

Architectural Implications of Graph Neural Networks

Shanghai Jiao Tong University(上海交通大学);Peking University(北京大学);Microsoft Research(微软研究院)

Zhihui Zhang, Jingwen Leng, Lingxiao Ma, Youshan Miao, Chao Li, Minyi Guo

摘要:

图神经网络(GNN)代表了一种新兴的深度学习模型,它对图结构进行操作。它正变得越来越受欢迎,由于其在许多图形相关的任务中实现的高精度。然而,GNN在系统和架构社区中并不像多层感知器和卷积神经网络那样被很好地理解。这项工作试图将GNN介绍给我们的社区。与之前只呈现GCN特征的工作相比,我们的工作覆盖了基于通用GNN描述框架的GNN工作负载的很大一部分。通过在两个广泛使用的库上构建模型,我们在推理阶段描述了GNN计算的通用和专用架构,并希望我们的工作可以促进更多的GNN系统和架构研究。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑