arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11079cs.LGcs.SIstat.ML
收藏

用于图的半监督学习的Graph Random神经网络

Graph Random Neural Network for Semi-Supervised Learning on Graphs

Microsoft Research(微软研究院);Tsinghua University(清华大学);WeBank Co., Ltd(微众银行股份有限公司);Bosch Center for Artificial Intelligence(博世人工智能中心)

Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang

摘要:

我们研究了图上的半监督学习问题,其中图神经网络(GNNs)已被广泛探索。然而,大多数现有的GNN固有地遭受过度平滑,非鲁棒性和弱泛化的限制,当标记的节点是稀缺的。在本文中,我们提出了一个简单而有效的框架-图随机神经网络(GRAND)-来解决这些问题。在GRAND中,我们首先设计一个随机传播策略来执行图数据增强。然后,我们利用一致性正则化来优化不同数据增强中未标记节点的预测一致性。在图基准数据集上进行的大量实验表明,GRAND在半监督节点分类上的性能明显优于最先进的GNN基线。最后,我们证明了GRAND减轻了过度平滑和非鲁棒性的问题,表现出比现有GNN更好的泛化行为。GRAND的源代码可在https://github.com/Grand20/grand上公开获得。

英文摘要:

We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, non-robustness, and weak-generalization when labeled nodes are scarce. In this paper, we propose a simple yet effective framework -- GRAPH RANDOM NEURAL NETWORKS (GRAND) -- to address these issues. In GRAND, we first design a random propagation strategy to perform graph data augmentation. Then we leverage consistency regularization to optimize the prediction consistency of unlabeled nodes across different data augmentations. Extensive experiments on graph benchmark datasets suggest that GRAND significantly outperforms state-of-the-art GNN baselines on semi-supervised node classification. Finally, we show that GRAND mitigates the issues of over-smoothing and non-robustness, exhibiting better generalization behavior than existing GNNs. The source code of GRAND is publicly available at https://github.com/Grand20/grand.

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。

↑