arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.11552cs.LGstat.ML
收藏

使用tf_geometric在TensorFlow中进行高效的图深度学习

Efficient Graph Deep Learning in TensorFlow with tf_geometric

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Hefei University of Technology(合肥工业大学);China Center for Information Industry Development(中国电子信息产业发展研究院)

Jun Hu, Shengsheng Qian, Quan Fang, Youze Wang, Quan Zhao, Huaiwen Zhang, Changsheng Xu

摘要:

我们引入了tf_geometric,这是一个用于图深度学习的高效友好库,它与TensorFlow 1.x和2.x都兼容。tf_geometric提供用于构建图神经网络(GNN)的内核库以及流行GNN的实现。内核库由构建高效GNN的基础设施组成,包括图数据结构、图映射缩减框架、图小批量策略等。这些基础设施使tf_geometric能够支持单图计算、多图计算、图小批量、分布式训练等;因此,tf_geometric可用于各种图深度学习任务,例如,转换节点分类、归纳节点分类、链接预测和图分类。基于内核库,tf_geometric为不同的任务实现了各种流行的GNN模型。为了方便GNN的实现,tf_geometric还提供了一些其他库,用于数据集管理,图采样等。与现有流行的GNN库不同,tf_geometric不仅提供面向对象编程(OOP)API,还提供函数式API,使tf_geometric能够处理高级图深度学习任务,如图元学习。tf_geometric的API是友好的,它们适合初学者和专家。在本文中,我们首先介绍了tf_geometric的框架。然后,我们在一些基准数据集上进行了实验,并报告了由tf_geometric实现的几种流行GNN模型的性能。

英文摘要:

We introduce tf_geometric, an efficient and friendly library for graph deep learning, which is compatible with both TensorFlow 1.x and 2.x. tf_geometric provides kernel libraries for building Graph Neural Networks (GNNs) as well as implementations of popular GNNs. The kernel libraries consist of infrastructures for building efficient GNNs, including graph data structures, graph map-reduce framework, graph mini-batch strategy, etc. These infrastructures enable tf_geometric to support single-graph computation, multi-graph computation, graph mini-batch, distributed training, etc.; therefore, tf_geometric can be used for a variety of graph deep learning tasks, such as transductive node classification, inductive node classification, link prediction, and graph classification. Based on the kernel libraries, tf_geometric implements a variety of popular GNN models for different tasks. To facilitate the implementation of GNNs, tf_geometric also provides some other libraries for dataset management, graph sampling, etc. Different from existing popular GNN libraries, tf_geometric provides not only Object-Oriented Programming (OOP) APIs, but also Functional APIs, which enable tf_geometric to handle advanced graph deep learning tasks such as graph meta-learning. The APIs of tf_geometric are friendly, and they are suitable for both beginners and experts. In this paper, we first present an overview of tf_geometric's framework. Then, we conduct experiments on some benchmark datasets and report the performance of several popular GNN models implemented by tf_geometric.

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。

↑