arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2009.02562cs.LGstat.ML
收藏

具有随机消息传递的置换等变邻近感知图神经网络

Permutation-equivariant and Proximity-aware Graph Neural Networks with Stochastic Message Passing

Tsinghua University(清华大学);Carnegie Mellon University(卡内基梅隆大学);Simon Fraser University(西蒙弗雷泽大学);Tencent(腾讯)

Ziwei Zhang, Chenhao Niu, Peng Cui, Jian Pei, Bo Zhang, Wenwu Zhu

摘要:

图神经网络(GNN)是一种新兴的基于图的机器学习模型。置换等方差和邻近感知是GNN非常需要的两个重要属性。这两个属性都需要解决一些具有挑战性的图形问题,例如寻找社区和领导者。在本文中,我们首先分析表明,现有的GNNs,主要是基于消息传递机制,不能同时保持这两个属性。然后,我们提出了随机消息传递(SMP)模型,一个通用的和简单的GNN保持接近意识和置换等变性。为了保持节点的邻近性,我们用随机节点表示来增强现有的GNN。我们从理论上证明了该机制可以使GNN保持节点的邻近性,同时,保持一定的参数化的置换等变性。我们报告了广泛的实验结果,在10个数据集上,并证明了SMP的有效性和效率的各种典型的图挖掘任务,包括图重建,节点分类,和链接预测。

英文摘要:

Graph neural networks (GNNs) are emerging machine learning models on graphs. Permutation-equivariance and proximity-awareness are two important properties highly desirable for GNNs. Both properties are needed to tackle some challenging graph problems, such as finding communities and leaders. In this paper, we first analytically show that the existing GNNs, mostly based on the message-passing mechanism, cannot simultaneously preserve the two properties. Then, we propose Stochastic Message Passing (SMP) model, a general and simple GNN to maintain both proximity-awareness and permutation-equivariance. In order to preserve node proximities, we augment the existing GNNs with stochastic node representations. We theoretically prove that the mechanism can enable GNNs to preserve node proximities, and at the same time, maintain permutation-equivariance with certain parametrization. We report extensive experimental results on ten datasets and demonstrate the effectiveness and efficiency of SMP for various typical graph mining tasks, including graph reconstruction, node classification, and link prediction.

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。

↑