{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T04:15:04Z","timestamp":1774152904049,"version":"3.50.1"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T00:00:00Z","timestamp":1720656000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Natural Science Foundation of Xiamen","award":["3502Z20227067"],"award-info":[{"award-number":["3502Z20227067"]}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2023J011430"],"award-info":[{"award-number":["2023J011430"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2023J011427"],"award-info":[{"award-number":["2023J011427"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Graph Neural Networks (GNNs) are deep learning models specifically designed for analyzing graph-structured data, capturing complex relationships and structures to improve analysis and prediction. A common task in GNNs is node classification, where each node in the graph is assigned a predefined category. The Graph Attention Network (GAT) is a popular variant of GNNs known for its ability to capture complex dependencies by assigning importance weights to nodes during information aggregation. However, the GAT\u2019s reliance on local attention mechanisms limits its effectiveness in capturing global information and long-range dependencies. To address this limitation, we propose a new attention mechanism called Global-Local Graph Attention (GLGA). Our mechanism enables the GAT to capture long-range dependencies and global graph structures while maintaining its ability to focus on local interactions. We evaluate our algorithm on three citation datasets (Cora, Citeseer, and Pubmed) using multiple metrics, demonstrating its superiority over other baseline models. The proposed GLGA mechanism has been proven to be an effective solution for improving node classification tasks.<\/jats:p>","DOI":"10.1093\/comjnl\/bxae060","type":"journal-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T18:55:48Z","timestamp":1720724148000},"page":"2959-2969","source":"Crossref","is-referenced-by-count":5,"title":["Global-local graph attention: unifying global and local attention for node classification"],"prefix":"10.1093","volume":"67","author":[{"given":"Keao","family":"Lin","sequence":"first","affiliation":[{"name":"College of Computer and Information Engineering, Xiamen University of Technology , Xiamen 361024 ,","place":["P. R. China"]}]},{"given":"Xiaozhu","family":"Xie","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Xiamen University of Technology , Xiamen 361024 ,","place":["P. R. China"]}]},{"given":"Wei","family":"Weng","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Xiamen University of Technology , Xiamen 361024 ,","place":["P. R. China"]},{"name":"Fujian Key Laboratory of Pattern Recognition and Image Understanding , Xiamen, 361024 \u00a0","place":["P. R. China"]}]},{"given":"Xiaofeng","family":"Du","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Xiamen University of Technology , Xiamen 361024 ,","place":["P. R. China"]}]}],"member":"286","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"2024101809310916100_ref1","doi-asserted-by":"crossref","first-page":"102538","DOI":"10.1016\/j.sbi.2023.102538","article-title":"Everything is connected: graph neural networks","volume":"79","author":"Veli\u010dkovi\u0107","year":"2023","journal-title":"Curr. Opin. Struct. Biol."},{"key":"2024101809310916100_ref2","doi-asserted-by":"crossref","first-page":"2393","DOI":"10.1093\/comjnl\/bxac086","article-title":"Multi-view spatial\u2013temporal graph neural network for traffic prediction","volume":"66","author":"Li","year":"2023","journal-title":"Comput. J."},{"key":"2024101809310916100_ref3","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1093\/comjnl\/bxad085","article-title":"Knowledge-aware Dual-Channel graph neural networks for denoising recommendation","volume":"67","author":"Zhang","year":"2023","journal-title":"Comput. J."},{"key":"2024101809310916100_ref4","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/978-1-4419-8462-3_5","article-title":"Node classification in social networks","author":"Bhagat","year":"2011","journal-title":"Soc. Netw. Data Anal."},{"key":"2024101809310916100_ref5","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1093\/comjnl\/bxab064","article-title":"Robust and dynamic graph convolutional network for multi-view data classification","volume":"64","author":"Peng","year":"2021","journal-title":"Comput. J."},{"key":"2024101809310916100_ref6","first-page":"1","article-title":"Benchmarking graph neural networks","volume":"24","author":"Dwivedi","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"2024101809310916100_ref7","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.ins.2023.02.054","article-title":"High-order graph attention network","volume":"630","author":"He","year":"2023","journal-title":"Inform. Sci."},{"key":"2024101809310916100_ref8","article-title":"How Attentive are Graph Attention Networks?","volume-title":"Int. Conf. on Learning Representations","author":"Brody","year":"2021"},{"key":"2024101809310916100_ref9","doi-asserted-by":"crossref","first-page":"106601","DOI":"10.1016\/j.engappai.2023.106601","article-title":"Graph features dynamic fusion learning driven by multi-head attention for large rotating machinery fault diagnosis with multi-sensor data","volume":"125","author":"Zhang","year":"2023","journal-title":"Eng. Appl. Artif. Intel."},{"key":"2024101809310916100_ref10","doi-asserted-by":"crossref","first-page":"3640","DOI":"10.3390\/app11083640","article-title":"Attention-enhanced graph convolutional networks for aspect-based sentiment classification with multi-head attention","volume":"11","author":"Xu","year":"2021","journal-title":"Appl. Sci."},{"key":"2024101809310916100_ref11","first-page":"1","article-title":"Hierarchical Graph Learning for Stock Market Prediction Via a Domain-Aware Graph Pooling Operator","volume-title":"IEEE Int. Conf. on Acoustics, Speech and Signal Processing","author":"Arya","year":"2023"},{"key":"2024101809310916100_ref12","first-page":"3734","article-title":"Self-attention graph pooling. In proc. of the int. conf. On","volume":"97","author":"Lee","year":"2019","journal-title":"Machine Learning"},{"key":"2024101809310916100_ref13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00138-021-01251-0","article-title":"Graph neural networks in node classification: survey and evaluation","volume":"33","author":"Xiao","year":"2022","journal-title":"Mach. Vis. Appl."},{"key":"2024101809310916100_ref14","first-page":"701","article-title":"Deepwalk: online learning of social representations","volume-title":"proc. of the 20th ACM SIGKDD int. conf. On knowledge discovery and data mining","author":"Perozzi","year":"2014"},{"key":"2024101809310916100_ref15","first-page":"855","article-title":"node2vec: scalable feature learning for networks","volume-title":"proc. of the 22nd ACM SIGKDD int. conf. On knowledge discovery and data mining","author":"Grover","year":"2016"},{"key":"2024101809310916100_ref16","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1016\/j.eswa.2019.07.006","article-title":"Learning deep neural networks for node classification","volume":"137","author":"Li","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"2024101809310916100_ref17","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"2024101809310916100_ref18","doi-asserted-by":"crossref","first-page":"119465","DOI":"10.1016\/j.ins.2023.119465","article-title":"To see further: knowledge graph-aware deep graph convolutional network for recommender systems","volume":"647","author":"Wang","year":"2023","journal-title":"Inform. Sci."},{"key":"2024101809310916100_ref19","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2023.3279929","article-title":"GraphSAGE-Based Dynamic Spatial\u2013Temporal Graph Convolutional Network for Traffic Prediction","volume-title":"IEEE Trans. Intell","author":"Liu","year":"2023"},{"key":"2024101809310916100_ref20","first-page":"76","article-title":"A deep hybrid GNN based on edge-conditioned and graph isomorphism network convolutions for PC-3 anticancer screening","volume-title":"Proc. of the 2023 10th Int. Conf. on Signal Processing and Integrated Networks (SPIN)","author":"Remigio","year":"2023"},{"key":"2024101809310916100_ref21","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2024101809310916100_ref22","doi-asserted-by":"crossref","first-page":"2263","DOI":"10.1007\/s10462-023-10577-2","article-title":"Attention-based graph neural networks: a survey","volume":"56","author":"Sun","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"2024101809310916100_ref23","article-title":"Graph Attention Networks","volume-title":"Proc. of the Int. Conf. on Learning Representations","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2024101809310916100_ref24","doi-asserted-by":"crossref","first-page":"3236","DOI":"10.1021\/acsomega.2c06702","article-title":"Attention-based graph neural network for molecular solubility prediction","volume":"8","author":"Ahmad","year":"2023","journal-title":"ACS Omega"},{"key":"2024101809310916100_ref25","first-page":"1548","article-title":"Masked label prediction: unified message passing model for semi-supervised classification","volume-title":"Proc. of the Thirtieth Int. Joint Conf. on Artificial Intelligence","author":"Shi","year":"2021"},{"key":"2024101809310916100_ref26","article-title":"Partition-based active learning for graph neural networks","author":"Ma","year":"2023","journal-title":"Transact. Mach. Learn. Res."},{"key":"2024101809310916100_ref27","first-page":"705","article-title":"GLGAT: Global-Local Graph Attention Network For Traffic Forecasting","volume-title":"Proc. of the 7th Int. Conf. on Information, Cybernetics, and Computational Social Systems (ICCSS)","author":"Shao","year":"2020"},{"key":"2024101809310916100_ref28","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-031-46305-1_1","article-title":"Attention-based global-local graph learning for dynamic facial expression recognition","volume-title":"proc. of the int. conf. On image and graphics","author":"Xie","year":"2023"},{"key":"2024101809310916100_ref29","first-page":"1","article-title":"GLTA-GCN: global-local temporal attention graph convolutional network for unsupervised skeleton-based action recognition","volume-title":"proc. of the 2022 IEEE int. conf. On multimedia and expo (ICME)","author":"Qiu","year":"2022"},{"key":"2024101809310916100_ref30","doi-asserted-by":"crossref","first-page":"110221","DOI":"10.1109\/ACCESS.2023.3285246","article-title":"A GNN architecture with local and global attention features for image classification","volume":"11","author":"Fei","year":"2023","journal-title":"IEEE Access"},{"key":"2024101809310916100_ref31","doi-asserted-by":"crossref","first-page":"20830","DOI":"10.1109\/ACCESS.2024.3361680","article-title":"Self-supervised hypergraph learning for enhanced multimodal representation","volume":"12","author":"Shu","year":"2024","journal-title":"IEEE Access"},{"key":"2024101809310916100_ref32","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","volume-title":"proc. of the int. conf. On machine learning","author":"Yang","year":"2016"},{"key":"2024101809310916100_ref33","first-page":"93","article-title":"Collective classification in network data","volume":"29","author":"Sen","year":"2008","journal-title":"AI Mag."},{"key":"2024101809310916100_ref34","article-title":"Deep Graph Infomax","volume-title":"Proc. of the Int. Conf. on Learning Representations","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"2024101809310916100_ref35","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"proc. of the int. conf. On Machine Learning","author":"Wu","year":"2019"},{"key":"2024101809310916100_ref36","article-title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","volume-title":"Proc. of the International Conf. on Learning Representations","author":"Chen","year":"2018"},{"key":"2024101809310916100_ref37","article-title":"Semi-Supervised Classification with Graph Convolutional Networks","volume-title":"Proc. of the Int. Conf. on Learning Representations","author":"Kipf","year":"2016"},{"key":"2024101809310916100_ref38","first-page":"30","article-title":"Inductive representation learning on large graphs","volume-title":"Adv. Neural Inf. Process. Syst","author":"Hamilton","year":"2017"},{"key":"2024101809310916100_ref39","first-page":"32","article-title":"Hyperbolic graph convolutional neural networks","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Chami","year":"2019"},{"key":"2024101809310916100_ref40","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1016\/j.future.2020.10.016","article-title":"Mutual teaching for graph convolutional networks","volume":"115","author":"Zhan","year":"2021","journal-title":"Future Gener Comput Syst"},{"key":"2024101809310916100_ref41","volume-title":"Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation","author":"Zhang","year":"2022"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/10\/2959\/59729436\/bxae060.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/67\/10\/2959\/59729436\/bxae060.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T09:31:30Z","timestamp":1729243890000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/67\/10\/2959\/7710998"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,11]]},"references-count":41,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,7,11]]},"published-print":{"date-parts":[[2024,10,12]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxae060","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,10]]},"published":{"date-parts":[[2024,7,11]]}}}