{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T04:46:05Z","timestamp":1786941965925,"version":"build-2736575974"},"reference-count":71,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100302"],"award-info":[{"award-number":["2018AAA0100302"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2024,7,31]]},"abstract":"<jats:p>Graph self-supervised representation learning has gained considerable attention and demonstrated remarkable efficacy in extracting meaningful representations from graphs, particularly in the absence of labeled data. Two representative methods in this domain are graph auto-encoding and graph contrastive learning. However, the former methods primarily focus on global structures, potentially overlooking some fine-grained information during reconstruction. The latter methods emphasize node similarity across correlated views in the embedding space, potentially neglecting the inherent global graph information in the original input space. Moreover, handling incomplete graphs in real-world scenarios, where original features are unavailable for certain nodes, poses challenges for both types of methods. To alleviate these limitations, we integrate masked graph auto-encoding and prototype-aware graph contrastive learning into a unified model to learn node representations in graphs. In our method, we begin by masking a portion of node features and utilize a specific decoding strategy to reconstruct the masked information. This process facilitates the recovery of graphs from a global or macro level and enables handling incomplete graphs easily. Moreover, we treat the masked graph and the original one as a pair of contrasting views, enforcing the alignment and uniformity between their corresponding node representations at a local or micro level. Last, to capture cluster structures from a meso level and learn more discriminative representations, we introduce a prototype-aware clustering consistency loss that is jointly optimized with the preceding two complementary objectives. Extensive experiments conducted on several datasets demonstrate that the proposed method achieves significantly better or competitive performance on downstream tasks, especially for graph clustering, compared with the state-of-the-art methods, showcasing its superiority in enhancing graph representation learning.<\/jats:p>","DOI":"10.1145\/3649143","type":"journal-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T12:26:57Z","timestamp":1708432017000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["ProtoMGAE: Prototype-Aware Masked Graph Auto-Encoder for Graph Representation Learning"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8612-4220","authenticated-orcid":false,"given":"Yimei","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0650-9564","authenticated-orcid":false,"given":"Caiyan","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Beijing Jiaotong University, and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"Proceedings of the 10th International Conference on Learning Representations","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2022. BEiT: BERT pre-training of image transformers. In Proceedings of the 10th International Conference on Learning Representations."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109631"},{"key":"e_1_3_2_4_2","first-page":"9912","volume-title":"Advances in Neural Information Processing Systems","author":"Caron Mathilde","year":"2020","unstructured":"Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2020. Unsupervised learning of visual features by contrasting cluster assignments. In Advances in Neural Information Processing Systems. 9912\u20139924."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.123"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I6.25858"},{"key":"e_1_3_2_7_2","first-page":"2292","volume-title":"Advances in Neural Information Processing Systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. In Advances in Neural Information Processing Systems. 2292\u20132300."},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_15"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.122653799"},{"key":"e_1_3_2_11_2","unstructured":"Jean-Bastien Grill Florian Strub Florent Altch\u00e9 Corentin Tallec Pierre H. Richemond Elena Buchatskaya Carl Doersch Bernardo \u00c1vila Pires Zhaohan Guo Mohammad Gheshlaghi Azar Bilal Piot Koray Kavukcuoglu R\u00e9mi Munos and Michal Valko. 2020. Bootstrap your own latent\u2014A new approach to self-supervised learning. In Advances in Neural Information Processing Systems. 21271\u201321284."},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2021.108310"},{"key":"e_1_3_2_13_2","first-page":"1024","volume-title":"Advances in Neural Information Processing Systems","author":"Hamilton William L.","year":"2017","unstructured":"William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems. 1024\u20131034."},{"key":"e_1_3_2_14_2","first-page":"4116","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Hassani Kaveh","year":"2020","unstructured":"Kaveh Hassani and Amir Hosein Khas Ahmadi. 2020. Contrastive multi-view representation learning on graphs. In Proceedings of the 37th International Conference on Machine Learning, Vol. 119. 4116\u20134126."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_16_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Hjelm R. Devon","year":"2019","unstructured":"R. Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Philip Bachman, Adam Trischler, and Yoshua Bengio. 2019. Learning deep representations by mutual information estimation and maximization. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583379"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539321"},{"key":"e_1_3_2_20_2","article-title":"Contrastive masked autoencoders are stronger vision learners","author":"Huang Zhicheng","year":"2022","unstructured":"Zhicheng Huang, Xiaojie Jin, Chengze Lu, Qibin Hou, Ming-Ming Cheng, Dongmei Fu, Xiaohui Shen, and Jiashi Feng. 2022. Contrastive masked autoencoders are stronger vision learners. arXiv preprint arXiv:2207.13532 (2022).","journal-title":"arXiv preprint arXiv:2207.13532"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3314973"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3166539"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/204"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449971"},{"key":"e_1_3_2_25_2","volume-title":"Proceedings of the International Workshop on Self-Supervised Learning for the Web (SSL \u201921) at the 2021 World Wide Web Conference","author":"Kefato Zekarias Tilahun","year":"2021","unstructured":"Zekarias Tilahun Kefato and Sarunas Girdzijauskas. 2021. Self-supervised graph neural networks without explicit negative sampling. In Proceedings of the International Workshop on Self-Supervised Learning for the Web (SSL \u201921) at the 2021 World Wide Web Conference."},{"key":"e_1_3_2_26_2","article-title":"Variational graph auto-encoders","author":"Kipf Thomas N.","year":"2016","unstructured":"Thomas N. Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016).","journal-title":"arXiv preprint arXiv:1611.07308"},{"key":"e_1_3_2_27_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_2_28_2","doi-asserted-by":"publisher","DOI":"10.1057\/jit.2010.6"},{"key":"e_1_3_2_29_2","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Lee Youngwan","year":"2023","unstructured":"Youngwan Lee, Jeffrey Ryan Willette, Jonghee Kim, Juho Lee, and Sung Ju Hwang. 2023. Exploring the role of mean teachers in self-supervised masked auto-encoders. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555809"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599546"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3191086"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3090866"},{"key":"e_1_3_2_34_2","first-page":"281","volume-title":"Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability","volume":"1","author":"MacQueen James B.","year":"1967","unstructured":"James B. MacQueen. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Vol. 1. 281\u2013297."},{"key":"e_1_3_2_35_2","article-title":"Wiki-CS: A Wikipedia-based benchmark for graph neural networks","author":"Mernyei P\u00e9ter","year":"2020","unstructured":"P\u00e9ter Mernyei and C\u0103t\u0103lina Cangea. 2020. Wiki-CS: A Wikipedia-based benchmark for graph neural networks. arXiv preprint arXiv:2007.02901 (2020).","journal-title":"arXiv preprint arXiv:2007.02901"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2932096"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/362"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00662"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186005"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380112"},{"key":"e_1_3_2_42_2","first-page":"1","article-title":"Ensemble learning","author":"Polikar Robi","year":"2012","unstructured":"Robi Polikar. 2012. Ensemble learning. In Ensemble Machine Learning: Methods and Applications. Springer, 1\u201334.","journal-title":"Ensemble Machine Learning: Methods and Applications."},{"key":"e_1_3_2_43_2","article-title":"Pitfalls of graph neural network evaluation","author":"Shchur Oleksandr","year":"2018","unstructured":"Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, and Stephan G\u00fcnnemann. 2018. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018).","journal-title":"arXiv preprint arXiv:1811.05868"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"e_1_3_2_45_2","volume-title":"Proceedings of the 8th International Conference on Learning Representations","author":"Sun Fan-Yun","year":"2020","unstructured":"Fan-Yun Sun, Jordan Hoffmann, Vikas Verma, and Jian Tang. 2020. InfoGraph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In Proceedings of the 8th International Conference on Learning Representations."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3385415"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3480244"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570404"},{"key":"e_1_3_2_49_2","volume-title":"Proceedings of the 10th International Conference on Learning Representations","author":"Tang Mingyue","year":"2022","unstructured":"Mingyue Tang, Pan Li, and Carl Yang. 2022. Graph auto-encoder via neighborhood Wasserstein reconstruction. In Proceedings of the 10th International Conference on Learning Representations."},{"key":"e_1_3_2_50_2","volume-title":"Proceedings of the 9th International Conference on Learning Representations Workshop on Geometrical and Topological Representation Learning","author":"Thakoor Shantanu","year":"2021","unstructured":"Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, R\u00e9mi Munos, Petar Veli\u010dkovi\u0107, and Michal Valko. 2021. Bootstrapped representation learning on graphs. In Proceedings of the 9th International Conference on Learning Representations Workshop on Geometrical and Topological Representation Learning."},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I8.26192"},{"key":"e_1_3_2_52_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Velickovic Petar","year":"2018","unstructured":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations."},{"key":"e_1_3_2_53_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations","author":"Velickovic Petar","year":"2019","unstructured":"Petar Velickovic, William Fedus, William L. Hamilton, Pietro Li\u00f2, Yoshua Bengio, and R. Devon Hjelm. 2019. Deep graph infomax. In Proceedings of the 7th International Conference on Learning Representations."},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132967"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/200"},{"key":"e_1_3_2_56_2","first-page":"9929","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In Proceedings of the 37th International Conference on Machine Learning, Vol. 119. 9929\u20139939."},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I3.25373"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815478"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3131584"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3164696"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3170559"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"e_1_3_2_63_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_2_64_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I9.26285"},{"key":"e_1_3_2_65_2","first-page":"40","volume-title":"Proceedings of the 33nd International Conference on Machine Learning","volume":"48","author":"Yang Zhilin","year":"2016","unstructured":"Zhilin Yang, William W. Cohen, and Ruslan Salakhutdinov. 2016. Revisiting semi-supervised learning with graph embeddings. In Proceedings of the 33nd International Conference on Machine Learning, Vol. 48. 40\u201348."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"e_1_3_2_67_2","first-page":"76","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang Hengrui","year":"2021","unstructured":"Hengrui Zhang, Qitian Wu, Junchi Yan, David Wipf, and Philip S. Yu. 2021. From canonical correlation analysis to self-supervised graph neural networks. In Advances in Neural Information Processing Systems. 76\u201389."},{"key":"e_1_3_2_68_2","first-page":"27127","article-title":"How mask matters: Towards theoretical understandings of masked autoencoders","author":"Zhang Qi","year":"2022","unstructured":"Qi Zhang, Yifei Wang, and Yisen Wang. 2022. How mask matters: Towards theoretical understandings of masked autoencoders. In Advances in Neural Information Processing Systems. 27127\u201327139.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3434767"},{"key":"e_1_3_2_70_2","article-title":"Deep graph contrastive representation learning","author":"Zhu Yanqiao","year":"2020","unstructured":"Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, and Liang Wang. 2020. Deep graph contrastive representation learning. arXiv preprint arXiv:2006.04131 (2020).","journal-title":"arXiv preprint arXiv:2006.04131"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449802"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3587268"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649143","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:50:01Z","timestamp":1750287001000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649143"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":71,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,7,31]]}},"alternative-id":["10.1145\/3649143"],"URL":"https:\/\/doi.org\/10.1145\/3649143","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2023-08-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}