{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T16:45:31Z","timestamp":1764089131547,"version":"3.45.0"},"reference-count":30,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010614","name":"Putian university","doi-asserted-by":"publisher","award":["JXJS202507"],"award-info":[{"award-number":["JXJS202507"]}],"id":[{"id":"10.13039\/501100010614","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Graph Convolutional Networks (GCNs) enhance node representations by aggregating information from neighboring nodes, but deeper layers often suffer from over-smoothing, where node embeddings become indistinguishable. Transformers enable global dependency modeling on graphs but suffer from high computational costs and can exacerbate over-smoothing when multiple attention layers are stacked. To address these issues, we propose GLADC, a novel framework designed for semi-supervised node classification. It integrates global linear attention for efficient long-range dependency capture and a dual constraint module for local propagation. The dual constraint consists of (1) column-wise random masking on the representation matrix to dynamically limit redundant information aggregation, and (2) row-wise contrastive constraint to explicitly increase inter-node distance and preserve distinctiveness. This design achieves linear-complexity global mixing while effectively countering representation homogenization. Extensive evaluations on seven real-world datasets demonstrate that GLADC delivers competitive performance and maintains robustness in deep architectures (up to 32 layers). An ablation study further confirms the synergistic effect of both constraints in alleviating over-smoothing and preventing premature convergence.<\/jats:p>","DOI":"10.3390\/a18120739","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T16:31:54Z","timestamp":1764088314000},"page":"739","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GLADC: Global Linear Attention and Dual Constraint for Mitigating Over-Smoothing in Graph Neural Networks"],"prefix":"10.3390","volume":"18","author":[{"given":"Zepeng","family":"Chen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Tiangong University, Tianjin 300387, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7694-2801","authenticated-orcid":false,"given":"Yang","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Information Technology and Engineering, Tianjin University of Technology and Education, Tianjin 300222, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tiangong University, Tianjin 300387, China"},{"name":"Fujian Key Laboratory of Financial Information Processing, Putian University, Putian 351100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanning","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Tiangong University, Tianjin 300387, China"},{"name":"College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"ref_1","unstructured":"Kipf, T.N., and Welling, M. (2017, January 24\u201326). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the International Conference on Learning Representations, Toulon, France."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Cheng, T., Bi, T., Ji, W., and Tian, C. (2024). Graph Convolutional Network for Image Restoration: A Survey. Mathematics, 12.","DOI":"10.3390\/math12132020"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"R\u00e9au, M., Renaud, N., Xue, L.C., and Bonvin, A.M. (2021). DeepRank-GNN: A graph neural network framework to learn patterns in protein\u2013protein interfaces. Bioinformatics, 39.","DOI":"10.1101\/2021.12.08.471762"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Tao, Z., and Huang, J. (2024). Research on recommender systems based on GCN. AIP Conference Proceedings, AIP Publishing.","DOI":"10.1063\/5.0222885"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Xu, W., Ma, B., Zhang, D., Zeng, F., Yao, J., Yang, H., and Du, Z. (2025). Linear attention based spatiotemporal multi graph GCN for traffic flow prediction. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-93179-y"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Huang, S., Xiang, H., Leng, C., and Xiao, F. (2024). Cross-Social-Network User Identification Based on Bidirectional GCN and MNF-UI Models. Electronics, 13.","DOI":"10.3390\/electronics13122351"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kenyeres, M., and Kenyeres, J. (2020). Average Consensus over Mobile Wireless Sensor Networks: Weight Matrix Guaranteeing Convergence without Reconfiguration of Edge Weights. Sensors, 20.","DOI":"10.3390\/s20133677"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s10723-022-09619-w","article-title":"An authentication-based secure data aggregation method in internet of things","volume":"20","author":"Barati","year":"2022","journal-title":"J. Grid Comput."},{"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","unstructured":"Rong, Y., Huang, W., Xu, T., and Huang, J. (2019, January 6\u20139). DropEdge: Towards Deep Graph Convolutional Networks on Node Classification. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Fang, T., Xiao, Z., Wang, C., Xu, J., Yang, X., and Yang, Y. (2023, January 7\u201314). Dropmessage: Unifying random dropping for graph neural networks. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i4.25545"},{"key":"ref_12","unstructured":"Guo, X., Wang, Y., Du, T., and Wang, Y. (2023, January 1\u20135). ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond. Proceedings of the 11th International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, W., Sheng, Z., Yin, Z., Jiang, Y., Xia, Y., Gao, J., Yang, Z., and Cui, B. (2022, January 14\u201318). Model degradation hinders deep graph neural networks. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/3534678.3539374"},{"key":"ref_14","unstructured":"Wu, Q., Zhao, W., Yang, C., Zhang, H., Nie, F., Jiang, H., Bian, Y., and Yan, J. (2023, January 10\u201316). Sgformer: Simplifying and empowering transformers for large-graph representations. Proceedings of the International Conference on Neural Information Processing Systems, New Orleans, LA, USA."},{"key":"ref_15","unstructured":"Gasteiger, J., Bojchevski, A., and G\u00fcnnemann, S. (2019, January 6\u20139). Predict then propagate: Graph neural networks meet personalized pagerank. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"114711","DOI":"10.1016\/j.eswa.2021.114711","article-title":"Graph convolutional neural networks with node transition probability-based message passing and DropNode regularization","volume":"174","author":"Do","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_17","unstructured":"Zhao, L., and Akoglu, L. (2019). PairNorm: Tackling Oversmoothing in GNNs. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhou, K., Dong, Y., Wang, K., Lee, W.S., Hooi, B., Xu, H., and Feng, J. (2021, January 1\u20135). Understanding and resolving performance degradation in deep graph convolutional networks. Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Virtual.","DOI":"10.1145\/3459637.3482488"},{"key":"ref_19","unstructured":"Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.I., and Jegelka, S. (2018, January 10\u201315). Representation learning on graphs with jumping knowledge networks. Proceedings of the International Conference on Machine Learning. PMLR, Stockholm, Sweden."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, G., Muller, M., Thabet, A., and Ghanem, B. (2019, January 27\u201328). DeepGCNs: Can GCNs go as deep as CNNs?. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00936"},{"key":"ref_21","unstructured":"Chen, M., Wei, Z., Huang, Z., Ding, B., and Li, Y. (2020, January 12\u201318). Simple and deep graph convolutional networks. Proceedings of the International Conference on Machine Learning. PMLR, Vienna, Austria."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Peng, F., Liu, K., Lu, X., Qian, Y., Yan, H., and Ma, C. (2024, January 25\u201329). TSC: A Simple Two-Sided Constraint against Over-Smoothing. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain.","DOI":"10.1145\/3637528.3671954"},{"key":"ref_23","unstructured":"Ying, C., Cai, T., Luo, S., Zheng, S., Ke, G., He, D., Shen, Y., and Liu, T.Y. (2021, January 6\u201314). Do transformers really perform badly for graph representation?. Proceedings of the International Conference on Neural Information Processing Systems, Virtual."},{"key":"ref_24","unstructured":"Wu, Z., Jain, P., Wright, M., Mirhoseini, A., Gonzalez, J.E., and Stoica, I. (2021, January 8\u201312). Representing long-range context for graph neural networks with global attention. Proceedings of the International Conference on Neural Information Processing Systems, Bali, Indonesia."},{"key":"ref_25","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. PMLR, Long Beach, CA, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chen, D., Lin, Y., Li, W., Li, P., Zhou, J., and Sun, X. (2020, January 7\u201312). Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref_27","first-page":"93","article-title":"Collective classification in network data","volume":"29","author":"Sen","year":"2008","journal-title":"AI Mag."},{"key":"ref_28","unstructured":"Shchur, O., Mumme, M., Bojchevski, A., and G\u00fcnnemann, S. (2018). Pitfalls of Graph Neural Network Evaluation. arXiv."},{"key":"ref_29","unstructured":"Lim, D., Hohne, F., Li, X., Huang, S.L., Gupta, V., Bhalerao, O., and Lim, S.N. (2021, January 6\u201314). Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. Proceedings of the International Conference on Neural Information Processing Systems, Virtual."},{"key":"ref_30","unstructured":"Platonov, O., Kuznedelev, D., Diskin, M., Babenko, A., and Prokhorenkova, L. (2023, January 1\u20135). A critical look at the evaluation of GNNs under heterophily: Are we really making progress?. Proceedings of the 11th International Conference on Learning Representations, Kigali, Rwanda."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/12\/739\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T16:35:36Z","timestamp":1764088536000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/18\/12\/739"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"references-count":30,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["a18120739"],"URL":"https:\/\/doi.org\/10.3390\/a18120739","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2025,11,25]]}}}