A Fast and Robust Attention-Free Heterogeneous Graph Convolutional Network

IF 7.5 3区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Yeyu Yan;Zhongying Zhao;Zhan Yang;Yanwei Yu;Chao Li
{"title":"A Fast and Robust Attention-Free Heterogeneous Graph Convolutional Network","authors":"Yeyu Yan;Zhongying Zhao;Zhan Yang;Yanwei Yu;Chao Li","doi":"10.1109/TBDATA.2024.3375152","DOIUrl":null,"url":null,"abstract":"Due to the widespread applications of heterogeneous graphs in the real world, heterogeneous graph neural networks (HGNNs) have developed rapidly and made a great success in recent years. To effectively capture the complex interactions in heterogeneous graphs, various attention mechanisms are widely used in designing HGNNs. However, the employment of these attention mechanisms brings two key problems: high computational complexity and poor robustness. To address these problems, we propose a \n<bold>Fast</b>\n and \n<bold>Ro</b>\nbust attention-free \n<bold>H</b>\neterogeneous \n<bold>G</b>\nraph \n<bold>C</b>\nonvolutional \n<bold>N</b>\network (FastRo-HGCN) without any attention mechanisms. Specifically, we first construct virtual links based on the topology similarity and feature similarity of the nodes to strengthen the connections between the target nodes. Then, we design type normalization to aggregate and transfer the intra-type and inter-type node information. The above methods are used to reduce the interference of noisy information. Finally, we further enhance the robustness and relieve the negative effects of oversmoothing with the self-loops of nodes. Extensive experimental results on three real-world datasets fully demonstrate that the proposed FastRo-HGCN significantly outperforms the state-of-the-art models.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"10 5","pages":"669-681"},"PeriodicalIF":7.5000,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Big Data","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10463147/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Due to the widespread applications of heterogeneous graphs in the real world, heterogeneous graph neural networks (HGNNs) have developed rapidly and made a great success in recent years. To effectively capture the complex interactions in heterogeneous graphs, various attention mechanisms are widely used in designing HGNNs. However, the employment of these attention mechanisms brings two key problems: high computational complexity and poor robustness. To address these problems, we propose a Fast and Ro bust attention-free H eterogeneous G raph C onvolutional N etwork (FastRo-HGCN) without any attention mechanisms. Specifically, we first construct virtual links based on the topology similarity and feature similarity of the nodes to strengthen the connections between the target nodes. Then, we design type normalization to aggregate and transfer the intra-type and inter-type node information. The above methods are used to reduce the interference of noisy information. Finally, we further enhance the robustness and relieve the negative effects of oversmoothing with the self-loops of nodes. Extensive experimental results on three real-world datasets fully demonstrate that the proposed FastRo-HGCN significantly outperforms the state-of-the-art models.
快速稳健的无注意力异构图卷积网络
由于异构图在现实世界中的广泛应用,异构图神经网络(HGNN)近年来发展迅速并取得了巨大成功。为了有效捕捉异构图中的复杂交互,各种注意力机制被广泛应用于异构图神经网络的设计中。然而,这些注意力机制的使用带来了两个关键问题:计算复杂度高和鲁棒性差。为了解决这些问题,我们提出了一种无需任何注意力机制的快速鲁棒无注意力异构图卷积网络(FastRo-HGCN)。具体来说,我们首先根据节点的拓扑相似性和特征相似性构建虚拟链接,以加强目标节点之间的连接。然后,我们设计了类型归一化,以聚合和传递类型内和类型间的节点信息。通过上述方法,可以减少噪声信息的干扰。最后,我们利用节点的自循环进一步增强了鲁棒性并缓解了过平滑的负面影响。在三个真实世界数据集上的广泛实验结果充分证明,所提出的 FastRo-HGCN 明显优于最先进的模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CiteScore
11.80
自引率
2.80%
发文量
114
期刊介绍: The IEEE Transactions on Big Data publishes peer-reviewed articles focusing on big data. These articles present innovative research ideas and application results across disciplines, including novel theories, algorithms, and applications. Research areas cover a wide range, such as big data analytics, visualization, curation, management, semantics, infrastructure, standards, performance analysis, intelligence extraction, scientific discovery, security, privacy, and legal issues specific to big data. The journal also prioritizes applications of big data in fields generating massive datasets.
×
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