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 2409.08217cs.LGcs.AI
收藏

CliquePH:通过团图上的持久同调为图神经网络提供高阶信息

CliquePH: Higher-Order Information for Graph Neural Networks through Persistent Homology on Clique Graphs

MediaTek Research(联发科研究院);Technical University of Munich(慕尼黑工业大学);University of Fribourg(弗里堡大学)

Davide Buffelli, Farzin Soleymani, Bastian Rieck

AI总结:

针对图神经网络难以捕捉高阶信息的问题,提出CliquePH方法,通过团图上的持久同调提取高阶拓扑信息,提升测试准确率达31%。

摘要:

图神经网络已成为从业者处理图分类和节点分类等图学习任务的默认选择。然而,主流图神经网络模型仍难以捕捉高阶信息,即超出成对交互的信息。近期研究表明,拓扑数据分析工具持久同调可丰富图神经网络的拓扑信息,否则这些信息无法被捕捉。计算0维(连通分量)和1维(环)的此类特征效率较高,但处理高阶结构时,复杂度为O(n^d)(n为节点数,d为结构阶数),难以扩展。本研究提出一种新方法,通过团图上的高效低维持久同调算法提取图中高阶结构信息。在标准基准数据集上,该方法可使测试准确率提升高达31%。

英文摘要:

Graph neural networks have become the default choice by practitioners for graph learning tasks such as graph classification and node classification. Nevertheless, popular graph neural network models still struggle to capture higher-order information, i.e., information that goes \emph{beyond} pairwise interactions. Recent work has shown that persistent homology, a tool from topological data analysis, can enrich graph neural networks with topological information that they otherwise could not capture. Calculating such features is efficient for dimension 0 (connected components) and dimension 1 (cycles). However, when it comes to higher-order structures, it does not scale well, with a complexity of $O(n^d)$, where $n$ is the number of nodes and $d$ is the order of the structures. In this work, we introduce a novel method that extracts information about higher-order structures in the graph while still using the efficient low-dimensional persistent homology algorithm. On standard benchmark datasets, we show that our method can lead to up to $31\%$ improvements in test accuracy.

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。

↑