{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T16:16:20Z","timestamp":1767197780193,"version":"3.48.0"},"reference-count":28,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["T2293771"],"award-info":[{"award-number":["T2293771"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Talent Scientific Fund of Lanzhou University","award":["561120208"],"award-info":[{"award-number":["561120208"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>The tasks of community detection in complex networks have garnered increasing attention from researchers. Concurrently, with the emergence of graph neural networks (GNNs), these models have rapidly become the mainstream approach for solving this task. However, GNNs frequently encounter the Laplacian oversmoothing problem, which dilutes the crucial neighborhood signals essential for community identification. These signals, particularly those from first-order neighbors, are the core source information defining community structure and identity. To address this contradiction, this paper proposes a novel training strategy focused on strengthening these key local signals. We design a multi-branch learning structure that injects a gradient into the GNN layer during backpropagation. This gradient is then modulated by the GNN\u2019s native message-passing path, precisely supplementing the parameters of the initial layers with first-order topological information. Based on this, we construct the network structure-informed GNN (NIGNN). A large number of experiments show that the proposed method achieves a 0.6\u20133.6% improvement in multiple indicators compared with the basic model in the community detection task, and performs well in the t-test. The framework has good general applicability and can be effectively applied to GCN, GAT, and GraphSAGE architectures, and shows strong robustness in networks with incomplete information. This work offers a novel solution for effectively preserving core local information in deep GNNs.<\/jats:p>","DOI":"10.3390\/e28010046","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T16:08:00Z","timestamp":1767197280000},"page":"46","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Branch Training Strategy for Enhancing Neighborhood Signals in GNNs for Community Detection"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5469-2965","authenticated-orcid":false,"given":"Yuning","family":"Guo","sequence":"first","affiliation":[{"name":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0655-0479","authenticated-orcid":false,"given":"Qiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Collaborative Innovation Center for Western Ecological Safety, Lanzhou University, Lanzhou 730000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2156-0432","authenticated-orcid":false,"given":"Linyuan","family":"L\u00fc","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"7821","DOI":"10.1073\/pnas.122653799","article-title":"Community structure in social and biological networks","volume":"99","author":"Girvan","year":"2002","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.physrep.2009.11.002","article-title":"Community detection in graphs","volume":"486","author":"Fortunato","year":"2010","journal-title":"Phys. Rep."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"026113","DOI":"10.1103\/PhysRevE.69.026113","article-title":"Finding and evaluating community structure in networks","volume":"69","author":"Newman","year":"2004","journal-title":"Phys. Rev. E"},{"key":"ref_4","first-page":"849","article-title":"On spectral clustering: Analysis and an algorithm","volume":"14","author":"Ng","year":"2001","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1073\/pnas.0605965104","article-title":"Resolution limit in community detection","volume":"104","author":"Fortunato","year":"2007","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_6","first-page":"27","article-title":"Community detection with graph neural networks","volume":"1050","author":"Bruna","year":"2017","journal-title":"Stat"},{"key":"ref_7","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":"ref_8","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Li, Q., Han, Z., and Wu, X.M. (2018, January 2\u20137). Deeper insights into graph convolutional networks for semi-supervised learning. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1086\/225469","article-title":"The strength of weak ties","volume":"78","author":"Granovetter","year":"1973","journal-title":"Am. J. Sociol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1146\/annurev.soc.27.1.415","article-title":"Birds of a feather: Homophily in social networks","volume":"27","author":"McPherson","year":"2001","journal-title":"Annu. Rev. Sociol."},{"key":"ref_12","unstructured":"Wu, F., Souza, A., Zhang, T., Fifty, C., Yu, T., and Weinberger, K. (2019, January 9\u201315). Simplifying graph convolutional networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_13","unstructured":"Kipf, T. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_14","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_15","unstructured":"Ruder, S. (2017). An overview of multi-task learning in deep neural networks. arXiv."},{"key":"ref_16","unstructured":"Kipf, T.N., and Welling, M. (2016). Variational graph auto-encoders. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Perozzi, B., Al-Rfou, R., and Skiena, S. (2014, January 24\u201327). Deepwalk: Online learning of social representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.","DOI":"10.1145\/2623330.2623732"},{"key":"ref_18","unstructured":"Yang, Z., Cohen, W., and Salakhudinov, R. (2016, January 19\u201324). Revisiting semi-supervised learning with graph embeddings. Proceedings of the International Conference on Machine Learning, New York, NY, USA."},{"key":"ref_19","unstructured":"Shchur, O., Mumme, M., Bojchevski, A., and G\u00fcnnemann, S. (2018). Pitfalls of graph neural network evaluation. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF01908075","article-title":"Comparing partitions","volume":"2","author":"Hubert","year":"1985","journal-title":"J. Classif."},{"key":"ref_21","first-page":"547","article-title":"\u00c9tude comparative de la distribution florale dans une portion des Alpes et des Jura","volume":"37","author":"Jaccard","year":"1901","journal-title":"Bull. Soc. Vaudoise Sci. Nat."},{"key":"ref_22","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/s40537-023-00876-4","article-title":"A review of graph neural networks: Concepts, architectures, techniques, challenges, datasets, applications, and future directions","volume":"11","author":"Khemani","year":"2024","journal-title":"J. Big Data"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1080\/00401706.1996.10484565","article-title":"The Nature of Statistical Learning Theory","volume":"38","author":"Sain","year":"1996","journal-title":"Technometrics"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.physa.2016.11.029","article-title":"Deep community detection in topologically incomplete networks","volume":"469","author":"Xin","year":"2017","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_26","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_27","unstructured":"Cai, C., and Wang, Y. (2020). A note on over-smoothing for graph neural networks. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"036106","DOI":"10.1103\/PhysRevE.76.036106","article-title":"Near linear time algorithm to detect community structures in large-scale networks","volume":"76","author":"Raghavan","year":"2007","journal-title":"Phys. Rev. E Stat. Nonlinear Soft Matter Phys."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/1\/46\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T16:11:52Z","timestamp":1767197512000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/1\/46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["e28010046"],"URL":"https:\/\/doi.org\/10.3390\/e28010046","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]}}}