{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:44:05Z","timestamp":1783035845946,"version":"3.54.6"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T00:00:00Z","timestamp":1638144000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ARO"},{"name":"NSF"},{"name":"NIH"},{"name":"Stanford Data Science Initiative"},{"DOI":"10.13039\/100014373","name":"Wu Tsai Neurosciences Institute","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100014373","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Chan Zuckerberg Biohub"},{"DOI":"10.13039\/100016443","name":"Amazon","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100016443","id-type":"DOI","asserted-by":"crossref"}]},{"name":"JPMorgan Chase"},{"name":"Docomo"},{"DOI":"10.13039\/100008238","name":"Hitachi","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100008238","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Intel"},{"name":"JD.com"},{"name":"KDDI"},{"DOI":"10.13039\/100007065","name":"NVIDIA","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100014206","name":"Dell","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100014206","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Toshiba"},{"DOI":"10.13039\/100016140","name":"Visa","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100016140","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100018368","name":"UnitedHealth Group","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100018368","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Inf. Syst."],"published-print":{"date-parts":[[2022,10,31]]},"abstract":"<jats:p>\n            Label Propagation Algorithm\u00a0(LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification, but LPA propagates node label information across the edges of the graph, while GCN propagates and transforms node feature information. However, while conceptually similar, theoretical relationship between LPA and GCN has not yet been systematically investigated. Moreover, it is unclear how LPA and GCN can be combined under a unified framework to improve the performance. Here we study the relationship between LPA and GCN in terms of\n            <jats:italic>feature\/label influence<\/jats:italic>\n            , in which we characterize how much the initial feature\/label of one node influences the final feature\/label of another node in GCN\/LPA. Based on our theoretical analysis, we propose an end-to-end model that combines GCN and LPA. In our unified model, edge weights are learnable, and the LPA serves as regularization to assist the GCN in learning proper edge weights that lead to improved performance. Our model can also be seen as learning the weights of edges based on node labels, which is more direct and efficient than existing feature-based attention models or topology-based diffusion models. In a number of experiments for semi-supervised node classification and knowledge-graph-aware recommendation, our model shows superiority over state-of-the-art baselines.\n          <\/jats:p>","DOI":"10.1145\/3490478","type":"journal-article","created":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T21:00:38Z","timestamp":1638219638000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":53,"title":["Combining Graph Convolutional Neural Networks and Label Propagation"],"prefix":"10.1145","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7474-8271","authenticated-orcid":false,"given":"Hongwei","family":"Wang","sequence":"first","affiliation":[{"name":"Stanford University, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jure","family":"Leskovec","sequence":"additional","affiliation":[{"name":"Stanford University, CA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,11,29]]},"reference":[{"key":"e_1_3_7_2_2","first-page":"21","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Abu-El-Haija Sami","year":"2019","unstructured":"Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, and Aram Galstyan. 2019. MixHop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In Proceedings of the 36th International Conference on Machine Learning. 21\u201329."},{"key":"e_1_3_7_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999923"},{"key":"e_1_3_7_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449927"},{"key":"e_1_3_7_5_2","volume-title":"Proceedings of the 13th International Conference on Artificial Intelligence and Statistics","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics."},{"key":"e_1_3_7_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2514360"},{"key":"e_1_3_7_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/3294771.3294869"},{"key":"e_1_3_7_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459267"},{"key":"e_1_3_7_9_2","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"Huang Qian","year":"2021","unstructured":"Qian Huang, Horace He, Abhay Singh, Ser-Nam Lim, and Austin R. Benson. 2021. Combining label propagation and simple models out-performs graph neural networks. In Proceedings of the 9th International Conference on Learning Representations."},{"key":"e_1_3_7_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01157"},{"key":"e_1_3_7_11_2","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999784"},{"key":"e_1_3_7_12_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations."},{"key":"e_1_3_7_13_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations."},{"key":"e_1_3_7_14_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Klicpera Johannes","year":"2019","unstructured":"Johannes Klicpera, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2019. Predict then propagate: Graph neural networks meet personalized pagerank. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_7_15_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455484"},{"key":"e_1_3_7_16_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305576"},{"key":"e_1_3_7_17_2","doi-asserted-by":"publisher","DOI":"10.5555\/3042573.3042694"},{"key":"e_1_3_7_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401944"},{"key":"e_1_3_7_19_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504468"},{"key":"e_1_3_7_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00981"},{"key":"e_1_3_7_21_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Liao Renjie","year":"2019","unstructured":"Renjie Liao, Zhizhen Zhao, Raquel Urtasun, and Richard S. Zemel. 2019. LanczosNet: Multi-scale deep graph convolutional networks. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_7_22_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Liu Yanbin","year":"2019","unstructured":"Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Eunho Yang, Sung Ju Hwang, and Yi Yang. 2019. Learning to propagate labels: Transductive propagation network for few-shot learning. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_7_23_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014424"},{"key":"e_1_3_7_24_2","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Qu Meng","year":"2019","unstructured":"Meng Qu, Yoshua Bengio, and Jian Tang. 2019. GMNN: Graph markov neural networks. In Proceedings of the 36th International Conference on Machine Learning."},{"key":"e_1_3_7_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168771"},{"key":"e_1_3_7_26_2","doi-asserted-by":"publisher","DOI":"10.5555\/2444851.2444861"},{"key":"e_1_3_7_27_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"issue":"3","key":"e_1_3_7_28_2","article-title":"Collective classification in network data","volume":"29","author":"Sen Prithviraj","year":"2008","unstructured":"Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Galligher, and Tina Eliassi-Rad. 2008. Collective classification in network data. AI Mag. 29, 3 (2008).","journal-title":"AI Mag."},{"key":"e_1_3_7_29_2","volume-title":"Neural Information Processing Systems Workshop on Relational Representation Learning","author":"Shchur Oleksandr","year":"2018","unstructured":"Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2018. Pitfalls of graph neural network evaluation. In Neural Information Processing Systems Workshop on Relational Representation Learning."},{"key":"e_1_3_7_30_2","article-title":"Masked label prediction: Unified message passing model for semi-supervised classification","author":"Shi Yunsheng","year":"2020","unstructured":"Yunsheng Shi, Zhengjie Huang, Wenjin Wang, Hui Zhong, Shikun Feng, and Yu Sun. 2020. Masked label prediction: Unified message passing model for semi-supervised classification. arXiv:2009.03509. Retrieved from https:\/\/arxiv.org\/abs\/2009.03509.","journal-title":"arXiv:2009.03509"},{"key":"e_1_3_7_31_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_7_32_2","article-title":"Attention-based graph neural network for semi-supervised learning","author":"Thekumparampil Kiran K.","year":"2018","unstructured":"Kiran K. Thekumparampil, Chong Wang, Sewoong Oh, and Li-Jia Li. 2018. Attention-based graph neural network for semi-supervised learning. arXiv:1803.03735. Retrieved from https:\/\/arxiv.org\/abs\/1803.03735.","journal-title":"arXiv:1803.03735"},{"key":"e_1_3_7_33_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Veli\u010dkovi\u0107 Petar","year":"2018","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations."},{"key":"e_1_3_7_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.190672"},{"key":"e_1_3_7_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271739"},{"key":"e_1_3_7_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330836"},{"key":"e_1_3_7_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450133"},{"key":"e_1_3_7_38_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Weston Jason","year":"2015","unstructured":"Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory networks. In Proceedings of the 3rd International Conference on Learning Representations."},{"key":"e_1_3_7_39_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367243.3367306"},{"key":"e_1_3_7_40_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Xu Keyulu","year":"2019","unstructured":"Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How powerful are graph neural networks? In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_7_41_2","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Xu Keyulu","year":"2018","unstructured":"Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. In Proceedings of the 35th International Conference on Machine Learning."},{"key":"e_1_3_7_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/3367471.3367605"},{"key":"e_1_3_7_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556259"},{"key":"e_1_3_7_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939673"},{"key":"e_1_3_7_45_2","article-title":"GaAN: Gated attention networks for learning on large and spatiotemporal graphs","author":"Zhang Jiani","year":"2018","unstructured":"Jiani Zhang, Xingjian Shi, Junyuan Xie, Hao Ma, Irwin King, and Dit-Yan Yeung. 2018. GaAN: Gated attention networks for learning on large and spatiotemporal graphs. arXiv:1803.07294. Retrieved from https:\/\/arxiv.org\/abs\/1803.07294.","journal-title":"arXiv:1803.07294"},{"key":"e_1_3_7_46_2","doi-asserted-by":"publisher","DOI":"10.5555\/2976456.2976655"},{"key":"e_1_3_7_47_2","doi-asserted-by":"publisher","DOI":"10.5555\/2976456.2976656"},{"key":"e_1_3_7_48_2","doi-asserted-by":"publisher","DOI":"10.5555\/2981345.2981386"},{"key":"e_1_3_7_49_2","doi-asserted-by":"publisher","DOI":"10.5555\/3041838.3041953"},{"key":"e_1_3_7_50_2","doi-asserted-by":"publisher","DOI":"10.5555\/1104523"}],"container-title":["ACM Transactions on Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3490478","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3490478","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3490478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:03Z","timestamp":1750188663000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3490478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,29]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,10,31]]}},"alternative-id":["10.1145\/3490478"],"URL":"https:\/\/doi.org\/10.1145\/3490478","relation":{},"ISSN":["1046-8188","1558-2868"],"issn-type":[{"value":"1046-8188","type":"print"},{"value":"1558-2868","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,29]]},"assertion":[{"value":"2021-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}