arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.16145cs.LG
收藏

研究大规模随机生成图上GNN的收敛性,考虑现实节点特征相关性

Investigating GNN Convergence on Large Randomly Generated Graphs with Realistic Node Feature Correlations

Live.co.uk(Live公司)

Mohammed Zain Ali Ahmed

AI总结:

本文提出一种生成具有相关节点特征的随机图方法,通过理论分析和实验证明在某些情况下GNN的收敛性可被避免,从而揭示其在现实图上的更强表达能力。

摘要:

现有许多研究分析了图神经网络在大规模随机图上的收敛行为。然而,大多数研究并未建模节点特征之间的相关性,这种相关性在各种现实网络中自然存在。因此,由此推导出的GNN局限性,由于这种收敛行为,不能真实反映GNN在现实图上应用时的表达能力。在本文中,我们将引入一种新的方法来生成具有相关节点特征的随机图。节点特征将被采样以确保相邻节点之间的相关性。作为我们采样方案选择的动机,我们将引用现实网络中展现的特性,特别是由巴塔伊-阿尔伯特模型捕捉的特性。理论分析将强烈表明在某些情况下可以避免收敛,我们将在使用我们新方法生成的大型随机图上进行实证验证。观察到的发散行为提供了证据,表明GNN可能比最初研究所建议的更具表现力,尤其是在现实图上。

英文摘要:

There are a number of existing studies analysing the convergence behaviour of graph neural networks on large random graphs. Unfortunately, the majority of these studies do not model correlations between node features, which would naturally exist in a variety of real-life networks. Consequently, the derived limitations of GNNs, resulting from such convergence behaviour, is not truly reflective of the expressive power of GNNs when applied to realistic graphs. In this paper, we will introduce a novel method to generate random graphs that have correlated node features. The node features will be sampled in such a manner to ensure correlation between neighbouring nodes. As motivation for our choice of sampling scheme, we will appeal to properties exhibited by real-life graphs, particularly properties that are captured by the Barabási-Albert model. A theoretical analysis will strongly indicate that convergence can be avoided in some cases, which we will empirically validate on large random graphs generated using our novel method. The observed divergent behaviour provides evidence that GNNs may be more expressive than initial studies would suggest, especially on realistic graphs.

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。

↑