基于注意力的图神经网络研究综述

IF 10.7 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Artificial Intelligence Review Pub Date : 2023-08-21 DOI:10.1007/s10462-023-10577-2
Chengcheng Sun, Chenhao Li, Xiang Lin, Tianji Zheng, Fanrong Meng, Xiaobin Rui, Zhixiao Wang
{"title":"基于注意力的图神经网络研究综述","authors":"Chengcheng Sun,&nbsp;Chenhao Li,&nbsp;Xiang Lin,&nbsp;Tianji Zheng,&nbsp;Fanrong Meng,&nbsp;Xiaobin Rui,&nbsp;Zhixiao Wang","doi":"10.1007/s10462-023-10577-2","DOIUrl":null,"url":null,"abstract":"<div><p>Graph neural networks (GNNs) aim to learn well-trained representations in a lower-dimension space for downstream tasks while preserving the topological structures. In recent years, attention mechanism, which is brilliant in the fields of natural language processing and computer vision, is introduced to GNNs to adaptively select the discriminative features and automatically filter the noisy information. To the best of our knowledge, due to the fast-paced advances in this domain, a systematic overview of attention-based GNNs is still missing. To fill this gap, this paper aims to provide a comprehensive survey on recent advances in attention-based GNNs. Firstly, we propose a novel two-level taxonomy for attention-based GNNs from the perspective of development history and architectural perspectives. Specifically, the upper level reveals the three developmental stages of attention-based GNNs, including graph recurrent attention networks, graph attention networks, and graph transformers. The lower level focuses on various typical architectures of each stage. Secondly, we review these attention-based methods following the proposed taxonomy in detail and summarize the advantages and disadvantages of various models. A model characteristics table is also provided for a more comprehensive comparison. Thirdly, we share our thoughts on some open issues and future directions of attention-based GNNs. We hope this survey will provide researchers with an up-to-date reference regarding applications of attention-based GNNs. In addition, to cope with the rapid development in this field, we intend to share the relevant latest papers as an open resource at https://github.com/sunxiaobei/awesome-attention-based-gnns.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"56 2","pages":"2263 - 2310"},"PeriodicalIF":10.7000,"publicationDate":"2023-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Attention-based graph neural networks: a survey\",\"authors\":\"Chengcheng Sun,&nbsp;Chenhao Li,&nbsp;Xiang Lin,&nbsp;Tianji Zheng,&nbsp;Fanrong Meng,&nbsp;Xiaobin Rui,&nbsp;Zhixiao Wang\",\"doi\":\"10.1007/s10462-023-10577-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>Graph neural networks (GNNs) aim to learn well-trained representations in a lower-dimension space for downstream tasks while preserving the topological structures. In recent years, attention mechanism, which is brilliant in the fields of natural language processing and computer vision, is introduced to GNNs to adaptively select the discriminative features and automatically filter the noisy information. To the best of our knowledge, due to the fast-paced advances in this domain, a systematic overview of attention-based GNNs is still missing. To fill this gap, this paper aims to provide a comprehensive survey on recent advances in attention-based GNNs. Firstly, we propose a novel two-level taxonomy for attention-based GNNs from the perspective of development history and architectural perspectives. Specifically, the upper level reveals the three developmental stages of attention-based GNNs, including graph recurrent attention networks, graph attention networks, and graph transformers. The lower level focuses on various typical architectures of each stage. Secondly, we review these attention-based methods following the proposed taxonomy in detail and summarize the advantages and disadvantages of various models. A model characteristics table is also provided for a more comprehensive comparison. Thirdly, we share our thoughts on some open issues and future directions of attention-based GNNs. We hope this survey will provide researchers with an up-to-date reference regarding applications of attention-based GNNs. In addition, to cope with the rapid development in this field, we intend to share the relevant latest papers as an open resource at https://github.com/sunxiaobei/awesome-attention-based-gnns.</p></div>\",\"PeriodicalId\":8449,\"journal\":{\"name\":\"Artificial Intelligence Review\",\"volume\":\"56 2\",\"pages\":\"2263 - 2310\"},\"PeriodicalIF\":10.7000,\"publicationDate\":\"2023-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Artificial Intelligence Review\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s10462-023-10577-2\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Artificial Intelligence Review","FirstCategoryId":"94","ListUrlMain":"https://link.springer.com/article/10.1007/s10462-023-10577-2","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 1

摘要

图神经网络(gnn)的目标是在保持拓扑结构的同时,为下游任务在低维空间中学习训练良好的表示。近年来,人们将自然语言处理和计算机视觉领域的研究成果——注意机制引入到gnn中,自适应地选择判别特征,自动过滤噪声信息。据我们所知,由于这一领域的快速发展,对基于注意力的gnn的系统概述仍然缺失。为了填补这一空白,本文旨在对基于注意力的gnn的最新进展进行全面调查。首先,我们从发展历史和架构的角度提出了一种新的基于关注的gnn的两级分类方法。具体而言,上层揭示了基于注意的gnn的三个发展阶段,包括图循环注意网络、图注意网络和图转换器。较低的层次侧重于每个阶段的各种典型架构。其次,我们根据所提出的分类方法对这些基于注意力的方法进行了详细的综述,并总结了各种模型的优缺点。还提供了模型特征表,以便进行更全面的比较。第三,我们对一些悬而未决的问题和基于关注的gnn的未来发展方向进行了讨论。我们希望这项调查能够为研究人员提供关于基于注意力的gnn应用的最新参考。此外,为了应对这一领域的快速发展,我们打算在https://github.com/sunxiaobei/awesome-attention-based-gnns上作为开放资源分享相关的最新论文。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Attention-based graph neural networks: a survey

Graph neural networks (GNNs) aim to learn well-trained representations in a lower-dimension space for downstream tasks while preserving the topological structures. In recent years, attention mechanism, which is brilliant in the fields of natural language processing and computer vision, is introduced to GNNs to adaptively select the discriminative features and automatically filter the noisy information. To the best of our knowledge, due to the fast-paced advances in this domain, a systematic overview of attention-based GNNs is still missing. To fill this gap, this paper aims to provide a comprehensive survey on recent advances in attention-based GNNs. Firstly, we propose a novel two-level taxonomy for attention-based GNNs from the perspective of development history and architectural perspectives. Specifically, the upper level reveals the three developmental stages of attention-based GNNs, including graph recurrent attention networks, graph attention networks, and graph transformers. The lower level focuses on various typical architectures of each stage. Secondly, we review these attention-based methods following the proposed taxonomy in detail and summarize the advantages and disadvantages of various models. A model characteristics table is also provided for a more comprehensive comparison. Thirdly, we share our thoughts on some open issues and future directions of attention-based GNNs. We hope this survey will provide researchers with an up-to-date reference regarding applications of attention-based GNNs. In addition, to cope with the rapid development in this field, we intend to share the relevant latest papers as an open resource at https://github.com/sunxiaobei/awesome-attention-based-gnns.

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
Artificial Intelligence Review
Artificial Intelligence Review 工程技术-计算机:人工智能
CiteScore
22.00
自引率
3.30%
发文量
194
审稿时长
5.3 months
期刊介绍: Artificial Intelligence Review, a fully open access journal, publishes cutting-edge research in artificial intelligence and cognitive science. It features critical evaluations of applications, techniques, and algorithms, providing a platform for both researchers and application developers. The journal includes refereed survey and tutorial articles, along with reviews and commentary on significant developments in the field.
期刊最新文献
Federated learning design and functional models: survey A systematic literature review of recent advances on context-aware recommender systems Escape: an optimization method based on crowd evacuation behaviors A multi-strategy boosted bald eagle search algorithm for global optimization and constrained engineering problems: case study on MLP classification problems Innovative solution suggestions for financing electric vehicle charging infrastructure investments with a novel artificial intelligence-based fuzzy decision-making modelling
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1