{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:08:24Z","timestamp":1753891704293,"version":"3.41.2"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T00:00:00Z","timestamp":1716249600000},"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. Neurorobot."],"abstract":"<jats:p>Graph Neural Networks (GNNs) have demonstrated significant potential as powerful tools for handling graph data in various fields. However, traditional GNNs often encounter limitations in information capture and generalization when dealing with complex and high-order graph structures. Concurrently, the sparse labeling phenomenon in graph data poses challenges in practical applications. To address these issues, we propose a novel graph contrastive learning method, TP-GCL, based on a tensor perspective. The objective is to overcome the limitations of traditional GNNs in modeling complex structures and addressing the issue of sparse labels. Firstly, we transform ordinary graphs into hypergraphs through clique expansion and employ high-order adjacency tensors to represent hypergraphs, aiming to comprehensively capture their complex structural information. Secondly, we introduce a contrastive learning framework, using the original graph as the anchor, to further explore the differences and similarities between the anchor graph and the tensorized hypergraph. This process effectively extracts crucial structural features from graph data. Experimental results demonstrate that TP-GCL achieves significant performance improvements compared to baseline methods across multiple public datasets, particularly showcasing enhanced generalization capabilities and effectiveness in handling complex graph structures and sparse labeled data.<\/jats:p>","DOI":"10.3389\/fnbot.2024.1381084","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T04:55:32Z","timestamp":1716267332000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["TP-GCL: graph contrastive learning from the tensor perspective"],"prefix":"10.3389","volume":"18","author":[{"given":"Mingyuan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhonglin","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanglin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujuan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhi","family":"Xiao","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":[[2024,5,21]]},"reference":[{"year":"2020","author":"Cai","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"119617","DOI":"10.1016\/j.ins.2023.119617","article-title":"Search for deep graph neural networks","volume":"649","author":"Feng","year":"2023","journal-title":"Inf. Sci."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3568022","article-title":"A survey of graph neural networks for recommender systems: challenges, methods, and directions","volume":"1","author":"Gao","year":"2023","journal-title":"ACM Trans. Recomm. Syst."},{"year":"2017","author":"Hamilton","key":"ref4"},{"year":"2020","author":"Hassani","key":"ref5"},{"year":"2022","author":"Hou","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"13953","DOI":"10.48550\/arXiv.2206.13953","article-title":"Raw-gnn: random walk aggregation based graph neural network","volume":"2022","author":"Jin","year":"2022","journal-title":"arXiv"},{"year":"2022","author":"Kim","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"02907","DOI":"10.48550\/arXiv.1609.02907","article-title":"Semi-supervised classification with graph convolutional networks","volume":"2016","author":"Kipf","year":"2016","journal-title":"arXiv"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1016\/j.ins.2022.06.075","article-title":"Influence maximization in social networks using graph embedding and graph neural network","volume":"607","author":"Kumar","year":"2022","journal-title":"Inf. Sci."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"109042","DOI":"10.1016\/j.patcog.2022.109042","article-title":"Exploratory adversarial attacks on graph neural networks for semi-supervised node classification","volume":"133","author":"Lin","year":"2023","journal-title":"Pattern Recogn."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2022.3172903","article-title":"Graph self-supervised learning: a survey","volume":"35","author":"Liu","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"118737","DOI":"10.1016\/j.eswa.2022.118737","article-title":"Link prediction approach combined graph neural network with capsule network","volume":"212","author":"Liu","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3568953","article-title":"Graph neural pre-training for recommendation with side information","volume":"41","author":"Liu","year":"2023","journal-title":"ACM Trans. Inf. Syst."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"106746","DOI":"10.1016\/j.knosys.2021.106746","article-title":"STGSN\u2013a spatial\u2013temporal graph neural network framework for time-evolving social networks","volume":"214","author":"Min","year":"2021","journal-title":"Knowl. Based Syst."},{"year":"2020","author":"Peng","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"118887","DOI":"10.1016\/j.eswa.2022.118887","article-title":"Enhanced graph neural network for session-based recommendation","volume":"213","author":"Sheng","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"775688","DOI":"10.3389\/fnbot.2021.775688","article-title":"Boosting-GNN: boosting algorithm for graph networks on imbalanced node classification[J]","volume":"15","author":"Shi","year":"2021","journal-title":"Front. Neurorobot."},{"year":"2022","author":"Shuai","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"5467","DOI":"10.48550\/arXiv.1911.05467","article-title":"ChebNet: efficient and stable constructions of deep neural networks with rectified power units using chebyshev approximations","volume":"2019","author":"Tang","year":"2019","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"10903","DOI":"10.48550\/arXiv.1710.10903","article-title":"Graph attention networks","volume":"2017","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"10341","DOI":"10.48550\/arXiv.1809.10341","article-title":"Deep graph infomax","volume":"2018","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"btad340","DOI":"10.1093\/bioinformatics\/btad340","article-title":"GraphscoreDTA: optimized graph neural network for protein\u2013ligand binding affinity prediction","volume":"39","author":"Wang","year":"2023","journal-title":"Bioinformatics"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3554981","article-title":"Dual subgraph-based graph neural network for friendship prediction in location-based social networks","volume":"17","author":"Wei","year":"2023","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"4216","DOI":"10.1109\/TKDE.2021.3131584","article-title":"Self-supervised learning on graphs: contrastive, generative, or predictive","volume":"35","author":"Wu","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"3136","DOI":"10.1007\/s10489-022-03592-3","article-title":"Rumor detection on social media using hierarchically aggregated feature via graph neural networks","volume":"53","author":"Xu","year":"2023","journal-title":"Appl. Intell."},{"year":"2022","author":"Yang","key":"ref27"},{"year":"2020","author":"Ye","key":"ref28"},{"year":"2020","author":"You","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"4077","DOI":"10.1109\/TKDE.2022.3142179","article-title":"Multi-view tensor graph neural networks through reinforced aggregation","volume":"35","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"bbad023","DOI":"10.1093\/bib\/bbad023","article-title":"Biological knowledge graph-guided investigation of immune therapy response in cancer with graph neural network","volume":"24","author":"Zhao","year":"2023","journal-title":"Brief. Bioinform."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2023.3341841","article-title":"Unsupervised structure-adaptive graph contrastive learning","volume":"1","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1007\/s11280-022-01070-x","article-title":"Multi-scale graph classification with shared graph neural network","volume":"26","author":"Zhou","year":"2023","journal-title":"World Wide Web"},{"key":"ref34","first-page":"2069","article-title":"Graph contrastive learning with adaptive augmentation","volume-title":"Proceedings of the ACM web conference","author":"Zhu","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"101867","DOI":"10.1016\/j.inffus.2023.101867","article-title":"Cross-view graph contrastive learning with hypergraph","volume":"99","author":"Zhu","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.ins.2023.03.057","article-title":"Similarity-navigated graph neural networks for node classification","volume":"633","author":"Zou","year":"2023","journal-title":"Inf. Sci."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1381084\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T04:55:38Z","timestamp":1716267338000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1381084\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,21]]},"references-count":36,"alternative-id":["10.3389\/fnbot.2024.1381084"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1381084","relation":{},"ISSN":["1662-5218"],"issn-type":[{"type":"electronic","value":"1662-5218"}],"subject":[],"published":{"date-parts":[[2024,5,21]]},"article-number":"1381084"}}