{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T16:39:03Z","timestamp":1789835943607,"version":"4.0.1"},"reference-count":33,"publisher":"China Science Publishing & Media Ltd.","issue":"3","license":[{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"vor","delay-in-days":43,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n               <jats:p>Heterogeneous information networks (HINs) have been extensively applied to real-world tasks, such as recommendation systems, social networks, and citation networks. While existing HIN representation learning methods can effectively learn the semantic and structural features in the network, little awareness was given to the distribution discrepancy of subgraphs within a single HIN. However, we find that ignoring such distribution discrepancy among subgraphs from multiple sources would hinder the effectiveness of graph embedding learning algorithms. This motivates us to propose SUMSHINE (Scalable Unsupervised Multi-Source Heterogeneous Information Network Embedding)\u2014a scalable unsupervised framework to align the embedding distributions among multiple sources of an HIN. Experimental results on real-world datasets in a variety of downstream tasks validate the performance of our method over the state-of-the-art heterogeneous information network embedding algorithms.<\/jats:p>","DOI":"10.1162\/dint_a_00200","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T22:07:19Z","timestamp":1676326039000},"page":"611-635","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":5,"title":["Source-Aware Embedding Training on Heterogeneous Information Networks"],"prefix":"10.3724","volume":"5","author":[{"given":"Tsai Hor","family":"Chan","sequence":"first","affiliation":[{"name":"Department of Statistics and Actuarial Science The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi Ho","family":"Wong","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Shen","sequence":"additional","affiliation":[{"name":"TCL Corporate Research (Hong Kong) Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosheng","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Statistics and Actuarial Science The University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2023,8,1]]},"reference":[{"key":"2023091215375892100_ref1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13321-020-00435-6","article-title":"KGCN: A graph-based deep learning framework for chemical structures","volume":"12","author":"Kojima","year":"2020","journal-title":"Journal of Cheminformatics"},{"key":"2023091215375892100_ref2","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"arXiv preprint arXiv:2005.00687","author":"Hu","year":"2020"},{"key":"2023091215375892100_ref3","article-title":"Translating embeddings for modeling multi-relational data","volume":"26","author":"Bordes","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023091215375892100_ref4","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v29i1.9491","article-title":"Learning entity and relation embeddings for knowledge graph completion","volume-title":"Twenty-ninth AAAI Conference on Arti-Ficial Intelligence","author":"Lin","year":"2015"},{"key":"2023091215375892100_ref5","article-title":"PyTorch-BigGraph: A large-scale graph embedding system","volume-title":"Proceedings of the 2nd SysML Conference","author":"Lerer","year":"2019"},{"key":"2023091215375892100_ref6","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/978-3-319-93417-4_18","article-title":"A multilin-gual event-centric temporal knowledge graph","volume-title":"European Semantic Web Conference","author":"Gottschalk","year":"2018"},{"key":"2023091215375892100_ref7","first-page":"2704","article-title":"Heterogeneous graph transformer","volume-title":"Proceedings of The Web Conference","author":"Hu","year":"2020"},{"key":"2023091215375892100_ref8","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.1145\/3308558.3313562","article-title":"Heterogeneous graph attention network","volume-title":"The World Wide Web Conference","author":"Wang","year":"2019"},{"key":"2023091215375892100_ref9","first-page":"1410","article-title":"Domain adaptive classification on heterogeneous information networks","volume-title":"International Joint Conference on Artificial Intelligence","author":"Yang","year":"2020"},{"key":"2023091215375892100_ref10","first-page":"4362","article-title":"Dane: Domain adaptive network embedding","volume-title":"International Joint Conference on Artificial Intelligence","author":"Zhang","year":"2019"},{"key":"2023091215375892100_ref11","doi-asserted-by":"crossref","first-page":"687","DOI":"10.3115\/v1\/P15-1067","article-title":"Knowledge graph embedding via dynamic mapping matrix","volume-title":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1, Long Papers)","author":"Ji","year":"2015"},{"key":"2023091215375892100_ref12","article-title":"Embedding entities and relations for learning and inference in knowledge bases","volume-title":"The 3rd International Conference on Learning Representations","author":"Yang","year":"2015"},{"key":"2023091215375892100_ref13","first-page":"2071","article-title":"Complex embeddings for simple link prediction","volume-title":"International conference on machine learning","author":"Trouillon","year":"2016"},{"key":"2023091215375892100_ref14","first-page":"809","article-title":"A three-way model for collective learning on multi-relational data","volume-title":"Proceedings of the 28th International Conference on International Conference on Machine Learning","author":"Nickel","year":"2011"},{"key":"2023091215375892100_ref15","first-page":"4463","article-title":"Multi-relational poincare graph embeddings","volume":"32","author":"Balazevic","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023091215375892100_ref16","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1145\/3097983.3098036","article-title":"Metapath2vec: Scalable representation learning for heterogeneous networks","volume-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Dong","year":"2017"},{"key":"2023091215375892100_ref17","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1007\/978-3-319-93037-4_16","article-title":"Meta-graph2vec: Complex semantic path augmented heterogeneous network embedding","volume-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","author":"Zhang","year":"2018"},{"key":"2023091215375892100_ref18","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kipf","year":"2017"},{"key":"2023091215375892100_ref19","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1145\/3366423.3380219","article-title":"Unsupervised domain adaptive graph convolutional networks","volume-title":"Proceedings of The Web Conference 2020","author":"Wu","year":"2020"},{"key":"2023091215375892100_ref20","article-title":"How powerful are graph neural networks?","volume-title":"International Conference on Learning Representations","author":"Xu","year":"2018"},{"key":"2023091215375892100_ref21","article-title":"Graph attention networks","volume-title":"arXiv preprint arXiv:1710.10903","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"2023091215375892100_ref22","article-title":"Dahgt: Domain adaptive heterogeneous graph transformer","volume-title":"arXiv preprint arXiv:2012.05688","author":"Huang","year":"2020"},{"key":"2023091215375892100_ref23","first-page":"7167","article-title":"Adversarial discriminative domain adaptation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Tzeng","year":"2017"},{"key":"2023091215375892100_ref24","first-page":"1930","article-title":"Minimax estimation of maximum mean discrepancy with radial kernels","volume":"29","author":"Tolstikhin","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2023091215375892100_ref25","first-page":"31","article-title":"Jensen-shannon divergence and hilbert space embedding","volume-title":"International Symposium on Information Theory, ISIT 2004, Proceedings","author":"Fuglede","year":"2004"},{"key":"2023091215375892100_ref26","first-page":"37","article-title":"Graph adaptive knowledge transfer for unsupervised domain adaptation","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Ding","year":"2018"},{"key":"2023091215375892100_ref27","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/978-3-642-41062-8_16","article-title":"Evaluation of Jensen-shannon distance over sparse data","volume-title":"International Conference on Similarity Search and Applications","author":"Connor","year":"2013"},{"issue":"1","key":"2023091215375892100_ref28","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"issue":"11","key":"2023091215375892100_ref29","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Communications of the ACM"},{"key":"2023091215375892100_ref30","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2020\/168","article-title":"Inductive link prediction for nodes having only attribute information","volume-title":"arXiv preprint arXiv:2007.08053","author":"Hao","year":"2020"},{"key":"2023091215375892100_ref31","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","volume-title":"arXiv preprint arXiv:1703.11008","author":"Dziugaite","year":"2017"},{"key":"2023091215375892100_ref32","doi-asserted-by":"crossref","first-page":"139","DOI":"10.18653\/v1\/D18-2024","article-title":"Openke: An open toolkit for knowledge embedding","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Han","year":"2018"},{"key":"2023091215375892100_ref33","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","volume-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds","author":"Wang","year":"2019"}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/611\/2158223\/dint_a_00200.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/dint\/article-pdf\/5\/3\/611\/2158223\/dint_a_00200.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T07:43:20Z","timestamp":1741938200000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.1162\/dint_a_00200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1162\/dint_a_00200","relation":{},"ISSN":["2641-435X"],"issn-type":[{"value":"2641-435X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}