{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T19:10:06Z","timestamp":1744053006304,"version":"3.40.3"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2024,11]]},"abstract":"<jats:p>Heterogeneous graph representation learning aims to extract low-dimensional node representations from complex networks with different types of entities and relationships. With the prevalence of heterogeneous information networks (HINs) in real-world scenarios, it is of vital significance for a network embedding model to handle heterogeneity and capture as much semantic information as possible. Existing works can be roughly categorized into meta-path-based and adjacent matrix-based methods depending on their definition of node neighborhoods. Meta-path-based methods aim to capture semantic similarities but require manual design. Adjacent matrix-based methods focus on structural information but may risk losing semantic context. In this work, we propose using schema instances representing node minimal complete contexts to embed HINs, aiming to integrate the advantages of both methods and avoid their deficiencies. We introduce Masked Schema based Graph Neural Networks (MSGNN), which combines schema instances with bi-level self-supervised learning and mask technique to acquire effective context representations. Furthermore, we propose a decomposition-reconstruction schema instance retrieval strategy to ensure efficient instance searching. Comprehensive experiments demonstrate that MSGNN outperforms state-of-the-art models. In the link prediction task, the F1-score has improved by up to 16.08% compared to the suboptimal method.<\/jats:p>","DOI":"10.14778\/3712221.3712226","type":"journal-article","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T18:03:04Z","timestamp":1744048984000},"page":"571-584","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MSGNN: Masked Schema based Graph Neural Networks"],"prefix":"10.14778","volume":"18","author":[{"given":"Hao","family":"Liu","sequence":"first","affiliation":[{"name":"Fudan University, Zhuhai Fudan Innovation Institute, Shanghai Key Laboratory of Data Science"}]},{"given":"Qianwen","family":"Yang","sequence":"additional","affiliation":[{"name":"Fudan University"}]},{"given":"Taoyong","family":"Cui","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University"}]}],"member":"320","published-online":{"date-parts":[[2025,4,7]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"e_1_2_1_2_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Cui Taoyong","year":"2024","unstructured":"Taoyong Cui and Yuhan Dong. 2024. Simple Orthogonal Graph Representation Learning (Student Abstract). In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 23462--23464."},{"key":"e_1_2_1_3_1","volume-title":"Geometry-enhanced pretraining on interatomic potentials. Nature Machine Intelligence","author":"Cui Taoyong","year":"2024","unstructured":"Taoyong Cui, Chenyu Tang, Mao Su, Shufei Zhang, Yuqiang Li, Lei Bai, Yuhan Dong, Xingao Gong, and Wanli Ouyang. 2024. Geometry-enhanced pretraining on interatomic potentials. Nature Machine Intelligence (2024), 1--9."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098036"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599441"},{"key":"e_1_2_1_6_1","volume-title":"Proceedings of the 2017 ACM on Conference on Information and Knowledge Management","author":"Lee Wang-Chien","year":"2017","unstructured":"Tao-yang Fu, Wang-Chien Lee, and Zhen Lei. 2017. HIN2Vec: Explore Metapaths in Heterogeneous Information Networks for Representation Learning. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (Singapore, Singapore) (CIKM '17). Association for Computing Machinery, New York, NY, USA, 1797--1806."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380297"},{"key":"e_1_2_1_9_1","article-title":"Role of ontology in semantic web","volume":"31","author":"Giri Kaushal","year":"2011","unstructured":"Kaushal Giri. 2011. Role of ontology in semantic web. DESIDOC Journal of Library & Information Technology 31, 2 (2011).","journal-title":"DESIDOC Journal of Library & Information Technology"},{"key":"e_1_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable Feature Learning for Networks. arXiv:1607.00653 [cs.SI]","DOI":"10.1145\/2939672.2939754"},{"key":"e_1_2_1_11_1","unstructured":"William L. Hamilton Rex Ying and Jure Leskovec. 2018. Inductive Representation Learning on Large Graphs. arXiv:1706.02216 [cs.SI]"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330970"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"e_1_2_1_14_1","first-page":"521","article-title":"Heterogeneous graph propagation network","volume":"35","author":"Ji Houye","year":"2021","unstructured":"Houye Ji, Xiao Wang, Chuan Shi, Bai Wang, and S Yu Philip. 2021. Heterogeneous graph propagation network. IEEE Transactions on Knowledge and Data Engineering 35, 1 (2021), 521--532.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","first-page":"3925","DOI":"10.1109\/TKDE.2021.3130712","article-title":"GCN for HIN via implicit utilization of attention and meta-paths","volume":"35","author":"Jin Di","year":"2021","unstructured":"Di Jin, Zhizhi Yu, Dongxiao He, Carl Yang, S Yu Philip, and Jiawei Han. 2021. GCN for HIN via implicit utilization of attention and meta-paths. IEEE Transactions on Knowledge and Data Engineering 35, 4 (2021), 3925--3937.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_2_1_16_1","volume-title":"Variational graph auto-encoders. arXiv preprint arXiv:1611.07308","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling. 2016. Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)."},{"key":"e_1_2_1_17_1","volume-title":"Deepergcn: All you need to train deeper gcns. arXiv preprint arXiv:2006.07739","author":"Li Guohao","year":"2020","unstructured":"Guohao Li, Chenxin Xiong, Ali Thabet, and Bernard Ghanem. 2020. Deepergcn: All you need to train deeper gcns. arXiv preprint arXiv:2006.07739 (2020)."},{"key":"e_1_2_1_18_1","unstructured":"Jintang Li Ruofan Wu Wangbin Sun Liang Chen Sheng Tian Liang Zhu Changhua Meng Zibin Zheng and Weiqiang Wang. 2023. What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders. arXiv:2205.10053 [cs.LG]"},{"key":"e_1_2_1_19_1","unstructured":"Zhiyuan Liu Yaorui Shi An Zhang Enzhi Zhang Kenji Kawaguchi Xiang Wang and Tat-Seng Chua. 2024. Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules. arXiv:2310.14753 [cs.LG]"},{"key":"e_1_2_1_20_1","unstructured":"Yuanfu Lu Chuan Shi Linmei Hu and Zhiyuan Liu. 2019. Relation Structure-Aware Heterogeneous Information Network Embedding. arXiv:1905.08027 [cs.SI]"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467350"},{"key":"e_1_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Qiheng Mao Zemin Liu Chenghao Liu and Jianling Sun. 2023. HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer. arXiv:2302.11329 [cs.LG]","DOI":"10.1145\/3543507.3583493"},{"key":"e_1_2_1_23_1","volume-title":"Social networks. Annual review of anthropology 3, 1","author":"Mitchell J Clyde","year":"1974","unstructured":"J Clyde Mitchell. 1974. Social networks. Annual review of anthropology 3, 1 (1974), 279--299."},{"key":"e_1_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Shirui Pan Ruiqi Hu Guodong Long Jing Jiang Lina Yao and Chengqi Zhang. 2019. Adversarially Regularized Graph Autoencoder for Graph Embedding. arXiv:1802.04407 [cs.LG]","DOI":"10.24963\/ijcai.2018\/362"},{"key":"e_1_2_1_25_1","volume-title":"Citation networks. Models of science dynamics: Encounters between complexity theory and information sciences","author":"Radicchi Filippo","year":"2011","unstructured":"Filippo Radicchi, Santo Fortunato, and Alessandro Vespignani. 2011. Citation networks. Models of science dynamics: Encounters between complexity theory and information sciences (2011), 233--257."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524728"},{"key":"e_1_2_1_27_1","volume-title":"ESWC 2018, Heraklion, Crete, Greece, June 3--7, 2018, proceedings 15","author":"Schlichtkrull Michael","year":"2018","unstructured":"Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In The semantic web: 15th international conference, ESWC 2018, Heraklion, Crete, Greece, June 3--7, 2018, proceedings 15. Springer, 593--607."},{"key":"e_1_2_1_28_1","volume-title":"Meta-path guided embedding for similarity search in large-scale heterogeneous information networks. arXiv preprint arXiv:1610.09769","author":"Shang Jingbo","year":"2016","unstructured":"Jingbo Shang, Meng Qu, Jialu Liu, Lance M Kaplan, Jiawei Han, and Jian Peng. 2016. Meta-path guided embedding for similarity search in large-scale heterogeneous information networks. arXiv preprint arXiv:1610.09769 (2016)."},{"key":"e_1_2_1_29_1","volume-title":"Wayne Xin Zhao, and Philip S. Yu","author":"Shi Chuan","year":"2017","unstructured":"Chuan Shi, Binbin Hu, Wayne Xin Zhao, and Philip S. Yu. 2017. Heterogeneous Information Network Embedding for Recommendation. arXiv:1711.10730 [cs.SI]"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2598561"},{"key":"e_1_2_1_31_1","volume-title":"Network embedding in biomedical data science. Briefings in bioinformatics 21, 1","author":"Su Chang","year":"2020","unstructured":"Chang Su, Jie Tong, Yongjun Zhu, Peng Cui, and Fei Wang. 2020. Network embedding in biomedical data science. Briefings in bioinformatics 21, 1 (2020), 182--197."},{"key":"e_1_2_1_32_1","volume-title":"Mining heterogeneous information networks: principles and methodologies","author":"Sun Yizhou","unstructured":"Yizhou Sun and Jiawei Han. 2012. Mining heterogeneous information networks: principles and methodologies. Morgan & Claypool Publishers."},{"key":"e_1_2_1_33_1","volume-title":"MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs. arXiv:2201.02534 [cs.LG]","author":"Tan Qiaoyu","year":"2022","unstructured":"Qiaoyu Tan, Ninghao Liu, Xiao Huang, Rui Chen, Soo-Hyun Choi, and Xia Hu. 2022. MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs. arXiv:2201.02534 [cs.LG]"},{"key":"e_1_2_1_34_1","volume-title":"Arnet-Miner: Extraction and Mining of Academic Social Networks. In KDD'08","author":"Tang Jie","year":"2008","unstructured":"Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, and Zhong Su. 2008. Arnet-Miner: Extraction and Mining of Academic Social Networks. In KDD'08. 990--998."},{"key":"e_1_2_1_35_1","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. arXiv:1710.10903 [stat.ML]"},{"key":"e_1_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Xiao Wang Houye Ji Chuan Shi Bai Wang Yanfang Ye Peng Cui and Philip S Yu. 2019. Heterogeneous graph attention network. In The world wide web conference. 2022--2032.","DOI":"10.1145\/3308558.3313562"},{"key":"e_1_2_1_37_1","volume-title":"Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning. arXiv preprint arXiv:2310.15523","author":"Wang Yuxiang","year":"2023","unstructured":"Yuxiang Wang, Xiao Yan, Chuang Hu, Fangcheng Fu, Wentao Zhang, Hao Wang, Shuo Shang, and Jiawei Jiang. 2023. Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning. arXiv preprint arXiv:2310.15523 (2023)."},{"key":"e_1_2_1_38_1","unstructured":"Felix Wu Amauri Souza Tianyi Zhang Christopher Fifty Tao Yu et al. 2019. Simplifying Graph Convolutional Networks. In ICML. 6861--6871."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539482"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539482"},{"key":"e_1_2_1_42_1","volume-title":"Graph transformer networks. Advances in neural information processing systems 32","author":"Yun Seongjun","year":"2019","unstructured":"Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, and Hyunwoo J Kim. 2019. Graph transformer networks. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557223"},{"key":"e_1_2_1_45_1","volume-title":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2600--2609","author":"Zhang Rui","year":"2022","unstructured":"Rui Zhang, Arthur Zimek, and Peter Schneider-Kamp. 2022. A simple metapath-free framework for heterogeneous network embedding. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2600--2609."},{"key":"e_1_2_1_46_1","unstructured":"Sixiao Zhang Hongxu Chen Haoran Yang Xiangguo Sun Philip S. Yu and Guandong Xu. 2022. Graph Masked Autoencoders with Transformers. arXiv:2202.08391 [cs.LG]"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16600"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.5555\/3491440.3491630"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00203"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3712221.3712226","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T18:28:56Z","timestamp":1744050536000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3712221.3712226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10.14778\/3712221.3712226"],"URL":"https:\/\/doi.org\/10.14778\/3712221.3712226","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2024,11]]},"assertion":[{"value":"2025-04-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}