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 1912.03046cs.LGstat.ML
收藏

双曲图注意力网络

Hyperbolic Graph Attention Network

Beijing University of Posts and Telecommunications(北京邮电大学);West Virginia University(西弗吉尼亚大学)

Yiding Zhang, Xiao Wang, Xunqiang Jiang, Chuan Shi, Yanfang Ye

摘要:

图神经网络(GNN)在处理图方面表现出了优越的性能,近年来引起了广泛的研究关注。然而,大多数现有的GNN模型主要是针对欧几里得空间中的图设计的。最近的研究已经证明,图形数据表现出非欧几里德潜在的解剖。不幸的是,到目前为止,很少有研究GNN在非欧几里德设置。为了弥补这一缺陷,本文首次尝试在双曲空间中研究了具有注意力机制的GNN。双曲GNN的研究有一些独特的挑战:由于双曲空间不是向量空间,因此向量运算(例如,向量加法、减法和标量乘法)不能被执行。为了解决这个问题,我们采用gyrovector空间,它提供了一个优雅的代数形式主义的双曲几何,变换的功能,在一个图,然后我们提出了双曲接近的注意力机制聚合的功能。此外,由于双曲空间中的数学运算可能比欧氏空间中的数学运算更复杂,我们进一步设计了一种新的加速策略,使用对数和指数映射来提高我们提出的模型的效率。在四个真实世界数据集上的综合实验结果表明,我们提出的双曲图注意力网络模型的性能,通过与其他国家的最先进的基线方法进行比较。

英文摘要:

Graph neural network (GNN) has shown superior performance in dealing with graphs, which has attracted considerable research attention recently. However, most of the existing GNN models are primarily designed for graphs in Euclidean spaces. Recent research has proven that the graph data exhibits non-Euclidean latent anatomy. Unfortunately, there was rarely study of GNN in non-Euclidean settings so far. To bridge this gap, in this paper, we study the GNN with attention mechanism in hyperbolic spaces at the first attempt. The research of hyperbolic GNN has some unique challenges: since the hyperbolic spaces are not vector spaces, the vector operations (e.g., vector addition, subtraction, and scalar multiplication) cannot be carried. To tackle this problem, we employ the gyrovector spaces, which provide an elegant algebraic formalism for hyperbolic geometry, to transform the features in a graph; and then we propose the hyperbolic proximity based attention mechanism to aggregate the features. Moreover, as mathematical operations in hyperbolic spaces could be more complicated than those in Euclidean spaces, we further devise a novel acceleration strategy using logarithmic and exponential mappings to improve the efficiency of our proposed model. The comprehensive experimental results on four real-world datasets demonstrate the performance of our proposed hyperbolic graph attention network model, by comparisons with other state-of-the-art baseline methods.

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。

↑