arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.06389cs.LGcs.SI
收藏

GRAND +:可扩展的图随机神经网络

GRAND+: Scalable Graph Random Neural Networks

Tsinghua University(清华大学);Beijing Institute of Technology(北京理工大学);Tencent Inc.(腾讯公司);Bosch Center for Artificial Intelligence(博世人工智能中心)

Wenzheng Feng, Yuxiao Dong, Tinglin Huang, Ziqi Yin, Xu Cheng, Evgeny Kharlamov, Jie Tang

摘要:

图神经网络(GNN)已被广泛用于图的半监督学习。最近的一项研究表明,图随机神经网络(GRAND)模型可以产生最先进的性能为这个问题。然而,它是困难的GRAND处理大规模的图形,因为它的有效性依赖于计算昂贵的数据增强程序。在这项工作中,我们提出了一个可扩展的和高性能的GNN框架GRAND+的半监督图学习。为了解决上述问题,我们在GRAND+中开发了一种广义前推(GFPush)算法来预先计算一般传播矩阵,并使用它以小批量方式执行图数据增强。我们表明,GFPush的低时间和空间复杂度使GRAND+能够有效地扩展到大型图形。此外,我们引入了一个置信度感知的一致性损失的模型优化的GRAND+,促进GRAND+的推广优势。我们在七个不同大小的公共数据集上进行了广泛的实验。结果表明,GRAND+ 1)能够扩展到大型图形,并且比现有的可扩展GNN花费更少的运行时间,2)可以在所有数据集上提供比全批和可扩展GNN一致的准确性改进。

英文摘要:

Graph neural networks (GNNs) have been widely adopted for semi-supervised learning on graphs. A recent study shows that the graph random neural network (GRAND) model can generate state-of-the-art performance for this problem. However, it is difficult for GRAND to handle large-scale graphs since its effectiveness relies on computationally expensive data augmentation procedures. In this work, we present a scalable and high-performance GNN framework GRAND+ for semi-supervised graph learning. To address the above issue, we develop a generalized forward push (GFPush) algorithm in GRAND+ to pre-compute a general propagation matrix and employ it to perform graph data augmentation in a mini-batch manner. We show that both the low time and space complexities of GFPush enable GRAND+ to efficiently scale to large graphs. Furthermore, we introduce a confidence-aware consistency loss into the model optimization of GRAND+, facilitating GRAND+'s generalization superiority. We conduct extensive experiments on seven public datasets of different sizes. The results demonstrate that GRAND+ 1) is able to scale to large graphs and costs less running time than existing scalable GNNs, and 2) can offer consistent accuracy improvements over both full-batch and scalable GNNs across all datasets.

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。

↑