arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.04843cs.LGcs.SIstat.ML
收藏

基于超图线扩展的半监督超图节点分类

Semi-supervised Hypergraph Node Classification on Hypergraph Line Expansion

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);George Mason University(乔治梅森大学)

Chaoqi Yang, Ruijie Wang, Shuochao Yao, Tarek Abdelzaher

AI总结:

本文提出超图线扩展方法,将顶点-超边对视为线节点以保留共现对称性,并验证其在五个数据集上半监督节点分类性能显著超越现有最优基线。

摘要:

以往的超图扩展仅在顶点层面或超边层面进行,因而忽略了数据共现的对称性,并导致信息损失。为解决该问题,本文将顶点与超边同等对待,提出了一种名为线扩展(line expansion, LE)的新超图表示形式用于超图学习。该新扩展通过将顶点-超边对视为“线节点”,从超图双射地诱导出一个同质结构。通过将超图归约为简单图,所提出的线扩展使现有图学习算法能够兼容高阶结构,并已被证明是多种超图扩展的统一框架。我们在五个超图数据集上评估了所提出的线扩展,结果表明我们的方法以显著优势超越了SOTA基线。

英文摘要:

Previous hypergraph expansions are solely carried out on either vertex level or hyperedge level, thereby missing the symmetric nature of data co-occurrence, and resulting in information loss. To address the problem, this paper treats vertices and hyperedges equally and proposes a new hypergraph formulation named the \emph{line expansion (LE)} for hypergraphs learning. The new expansion bijectively induces a homogeneous structure from the hypergraph by treating vertex-hyperedge pairs as "line nodes". By reducing the hypergraph to a simple graph, the proposed \emph{line expansion} makes existing graph learning algorithms compatible with the higher-order structure and has been proven as a unifying framework for various hypergraph expansions. We evaluate the proposed line expansion on five hypergraph datasets, the results show that our method beats SOTA baselines by a significant margin.

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。

↑