利用最密集重叠子图在超图神经网络中建立超edge 模型

Mehrad Soltani, Luis Rueda
{"title":"利用最密集重叠子图在超图神经网络中建立超edge 模型","authors":"Mehrad Soltani, Luis Rueda","doi":"arxiv-2409.10340","DOIUrl":null,"url":null,"abstract":"Hypergraphs tackle the limitations of traditional graphs by introducing {\\em\nhyperedges}. While graph edges connect only two nodes, hyperedges connect an\narbitrary number of nodes along their edges. Also, the underlying\nmessage-passing mechanisms in Hypergraph Neural Networks (HGNNs) are in the\nform of vertex-hyperedge-vertex, which let HGNNs capture and utilize richer and\nmore complex structural information than traditional Graph Neural Networks\n(GNNs). More recently, the idea of overlapping subgraphs has emerged. These\nsubgraphs can capture more information about subgroups of vertices without\nlimiting one vertex belonging to just one group, allowing vertices to belong to\nmultiple groups or subgraphs. In addition, one of the most important problems\nin graph clustering is to find densest overlapping subgraphs (DOS). In this\npaper, we propose a solution to the DOS problem via Agglomerative Greedy\nEnumeration (DOSAGE) algorithm as a novel approach to enhance the process of\ngenerating the densest overlapping subgraphs and, hence, a robust construction\nof the hypergraphs. Experiments on standard benchmarks show that the DOSAGE\nalgorithm significantly outperforms the HGNNs and six other methods on the node\nclassification task.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Hyperedge Modeling in Hypergraph Neural Networks by using Densest Overlapping Subgraphs\",\"authors\":\"Mehrad Soltani, Luis Rueda\",\"doi\":\"arxiv-2409.10340\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Hypergraphs tackle the limitations of traditional graphs by introducing {\\\\em\\nhyperedges}. While graph edges connect only two nodes, hyperedges connect an\\narbitrary number of nodes along their edges. Also, the underlying\\nmessage-passing mechanisms in Hypergraph Neural Networks (HGNNs) are in the\\nform of vertex-hyperedge-vertex, which let HGNNs capture and utilize richer and\\nmore complex structural information than traditional Graph Neural Networks\\n(GNNs). More recently, the idea of overlapping subgraphs has emerged. These\\nsubgraphs can capture more information about subgroups of vertices without\\nlimiting one vertex belonging to just one group, allowing vertices to belong to\\nmultiple groups or subgraphs. In addition, one of the most important problems\\nin graph clustering is to find densest overlapping subgraphs (DOS). In this\\npaper, we propose a solution to the DOS problem via Agglomerative Greedy\\nEnumeration (DOSAGE) algorithm as a novel approach to enhance the process of\\ngenerating the densest overlapping subgraphs and, hence, a robust construction\\nof the hypergraphs. Experiments on standard benchmarks show that the DOSAGE\\nalgorithm significantly outperforms the HGNNs and six other methods on the node\\nclassification task.\",\"PeriodicalId\":501032,\"journal\":{\"name\":\"arXiv - CS - Social and Information Networks\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Social and Information Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.10340\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Social and Information Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.10340","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

超图通过引入{emhyperedges}解决了传统图的局限性。图的边只连接两个节点,而超图则沿边连接任意数量的节点。此外,超图神经网络(HGNN)的基本信息传递机制是顶点-超边-顶点的形式,这使得 HGNN 能够捕捉和利用比传统图神经网络(GNN)更丰富、更复杂的结构信息。最近,出现了重叠子图的概念。这些子图可以捕捉更多的顶点子群信息,而不会限制一个顶点只属于一个群组,从而允许顶点属于多个群组或子图。此外,图聚类中最重要的问题之一是找到最密集的重叠子图(DOS)。在本文中,我们提出了一种通过聚合贪婪枚举(Agglomerative GreedyEnumeration,简称 "DABA")算法解决 DOS 问题的方法,这是一种新颖的方法,可以增强最密集重叠子图的生成过程,从而稳健地构建超图。在标准基准上进行的实验表明,在节点分类任务上,该算法明显优于 HGNN 和其他六种方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Hyperedge Modeling in Hypergraph Neural Networks by using Densest Overlapping Subgraphs
Hypergraphs tackle the limitations of traditional graphs by introducing {\em hyperedges}. While graph edges connect only two nodes, hyperedges connect an arbitrary number of nodes along their edges. Also, the underlying message-passing mechanisms in Hypergraph Neural Networks (HGNNs) are in the form of vertex-hyperedge-vertex, which let HGNNs capture and utilize richer and more complex structural information than traditional Graph Neural Networks (GNNs). More recently, the idea of overlapping subgraphs has emerged. These subgraphs can capture more information about subgroups of vertices without limiting one vertex belonging to just one group, allowing vertices to belong to multiple groups or subgraphs. In addition, one of the most important problems in graph clustering is to find densest overlapping subgraphs (DOS). In this paper, we propose a solution to the DOS problem via Agglomerative Greedy Enumeration (DOSAGE) algorithm as a novel approach to enhance the process of generating the densest overlapping subgraphs and, hence, a robust construction of the hypergraphs. Experiments on standard benchmarks show that the DOSAGE algorithm significantly outperforms the HGNNs and six other methods on the node classification task.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信