{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:01:34Z","timestamp":1772553694852,"version":"3.50.1"},"reference-count":18,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T00:00:00Z","timestamp":1700697600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>The emergence of deep learning has not only brought great changes in the field of image recognition, but also achieved excellent node classification performance in graph neural networks. However, the existing graph neural network framework often uses methods based on spatial domain or spectral domain to capture network structure features. This process captures the local structural characteristics of graph data, and the convolution process has a large amount of calculation. It is necessary to use multi-channel or deep neural network structure to achieve the goal of modeling the high-order structural characteristics of the network. Therefore, this paper proposes a linear graph neural network framework [Linear Graph Neural Network (LGNN)] with superior performance. The model first preprocesses the input graph, and uses symmetric normalization and feature normalization to remove deviations in the structure and features. Then, by designing a high-order adjacency matrix propagation mechanism, LGNN enables nodes to iteratively aggregate and learn the feature information of high-order neighbors. After obtaining the node representation of the network structure, LGNN uses a simple linear mapping to maintain computational efficiency and obtain the final node representation. The experimental results show that the performance of the LGNN algorithm in some tasks is slightly worse than that of the existing mainstream graph neural network algorithms, but it shows or exceeds the machine learning performance of the existing algorithms in most graph neural network performance evaluation tasks, especially on sparse networks.<\/jats:p>","DOI":"10.3389\/fncom.2023.1288842","type":"journal-article","created":{"date-parts":[[2023,11,23]],"date-time":"2023-11-23T11:51:29Z","timestamp":1700740289000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["LGNN: a novel linear graph neural network algorithm"],"prefix":"10.3389","volume":"17","author":[{"given":"Shujuan","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhonglin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haixing","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,11,23]]},"reference":[{"key":"ref1","first-page":"1407","article-title":"GRAND: graph neural diffusion","author":"Chamberlain","year":"2021"},{"key":"ref2","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"Defferrard","year":"2016"},{"key":"ref3","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proceedings of the 28th international conference on neural information processing systems","author":"Duvenaud","year":"2015"},{"key":"ref9001","article-title":"A generalization of transformer networks to graphs. arXiv [Preprint]","author":"Dwivedi","year":"2020"},{"key":"ref4","first-page":"855","article-title":"node2vec: scalable feature learning for networks","author":"Grover","year":"2016"},{"key":"ref5","first-page":"478","article-title":"Rec-GNN: research on social recommendation based on graph neural networks","author":"Guangquan","year":"2022"},{"key":"ref6","first-page":"1024","article-title":"Inductive representation learning on large graphs. Proceedings of the","author":"Hamilton","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","article-title":"Review on convolutional neural networks (CNN) in vegetation remote sensing","volume":"173","author":"Kattenborn","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref8","first-page":"1","article-title":"Deep auto-encoder neural networks in reinforcement learning","author":"Lange","year":"2010"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.neucom.2013.09.055","article-title":"Autoencoder for words","volume":"139","author":"Liou","year":"2014","journal-title":"Neurocomputing"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"108768","DOI":"10.1016\/j.asoc.2022.108768","article-title":"A two-stage intrusion detection system with auto-encoder and LSTMs","volume":"121","author":"Mushtaq","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref11","first-page":"701","article-title":"DeepWalk: online learning of social representations","author":"Perozzi","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1017\/S0962492900002919","article-title":"Approximation theory of the MLP model in neural networks","volume":"8","author":"Pinkus","year":"1999","journal-title":"Acta Numer."},{"key":"ref13","first-page":"1067","article-title":"LINE: large-scale information network embedding","author":"Tang","year":"2015"},{"key":"ref14","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","first-page":"10","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"ref16","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"ref17","volume-title":"Comparative study of CNN and RNN for natural language processing","author":"Yin","year":"2017"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1288842\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T13:00:36Z","timestamp":1702040436000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1288842\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,23]]},"references-count":18,"alternative-id":["10.3389\/fncom.2023.1288842"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2023.1288842","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,23]]},"article-number":"1288842"}}