{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T18:52:05Z","timestamp":1758394325965,"version":"3.37.3"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2021,5,3]],"date-time":"2021-05-03T00:00:00Z","timestamp":1620000000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876138","61602354"],"award-info":[{"award-number":["61876138","61602354"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Most existing heterogeneous information network (HIN) embedding methods focus on static environments while neglecting the evolving characteristic of real-world networks. Although several dynamic embedding methods have been proposed, they are merely designed for homogeneous networks and cannot be directly applied in heterogeneous environments. To tackle above challenges, we propose a novel framework for incorporating temporal information into HIN embedding, named multi-view dynamic HIN embedding (MDHNE), which can efficiently preserve evolution patterns of implicit relationships from different views in updating node vectors over time. We first transform HIN to a series of homogeneous networks corresponding to different views. Then our proposed MDHNE applies recurrent neural network (RNN) to incorporate evolving pattern of complex network structure and semantic relationships between nodes into latent embedding spaces, and thus the node vectors from multiple views can be learned and updated when HIN evolves over time. Moreover, we come up with an attention-based fusion mechanism, which can automatically infer weights of latent vectors corresponding to different views by minimizing the objective function specific for different mining tasks. Extensive experiments clearly demonstrate that our MDHNE model outperforms state-of-the-art baselines on three real-world dynamic datasets for different network mining tasks.<\/jats:p>","DOI":"10.1093\/comjnl\/bxab041","type":"journal-article","created":{"date-parts":[[2021,4,1]],"date-time":"2021-04-01T19:14:43Z","timestamp":1617304483000},"page":"2016-2033","source":"Crossref","is-referenced-by-count":4,"title":["Multi-view Dynamic Heterogeneous Information Network Embedding"],"prefix":"10.1093","volume":"65","author":[{"given":"Zhenghao","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology , Xidian University, Xi\u2019an, 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbin","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology , Xidian University, Xi\u2019an, 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinglin","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology , Xidian University, Xi\u2019an, 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,5,3]]},"reference":[{"key":"2022081612371828100_ref1","first-page":"1313","volume-title":"IEEE 13th Int. Conf. Data Mining","author":"Zhuang","year":"2013"},{"key":"2022081612371828100_ref2","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1109\/ICDM.2016.0127","volume-title":"IEEE 16th Int. Conf. Data Mining (ICDM)","author":"Li","year":"2016"},{"key":"2022081612371828100_ref3","first-page":"813","volume-title":"Thirty-Sec. AAAI Conf. Artif. Intell.","author":"Zhou","year":"2018"},{"key":"2022081612371828100_ref4","first-page":"686","volume-title":"Proc. 14th ACM SIGKDD Int. Conf. on Knowl. Disc. Data Mining","author":"Tong","year":"2008"},{"key":"2022081612371828100_ref5","first-page":"677","volume-title":"Proc. 14th ACM SIGKDD Int. Conf. Knowl. Disc. Data Mining","author":"Tang","year":"2008"},{"key":"2022081612371828100_ref6","first-page":"261","volume-title":"Proc. SIAM Int. Conf. Data Mining","author":"Ning","year":"2007"},{"key":"2022081612371828100_ref7","first-page":"355","volume-title":"Proc. 2011 SIAM Int. Conf. Data Mining","author":"Aggarwal","year":"2011"},{"key":"2022081612371828100_ref8","first-page":"1","article-title":"Dyngem: Deep Embedding Method for Dynamic Graphs","volume":"1805.11273","author":"Goyal","year":"2018","journal-title":"arXiv Preprint"},{"key":"2022081612371828100_ref9","doi-asserted-by":"crossref","first-page":"2765","DOI":"10.1109\/TKDE.2016.2591009","article-title":"Scalable Temporal Latent Space Inference for Link Prediction in Dynamic Social Networks","volume":"28","author":"Zhu","year":"2016","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2022081612371828100_ref10","first-page":"754","volume-title":"Thirty-Sec. AAAI Conf. Artif. Intell.","author":"Zhang","year":"2018"},{"key":"2022081612371828100_ref11","first-page":"19","article-title":"Relationship Prediction in Dynamic Heterogeneous Information Networks","author":"Fard","year":"2019"},{"key":"2022081612371828100_ref12","first-page":"861","volume-title":"Proc. 42nd Int. ACM SIGIR Conf. Res. Dev. Inf. Retriev.","author":"Bian","year":"2019"},{"key":"2022081612371828100_ref13","doi-asserted-by":"crossref","first-page":"134782","DOI":"10.1109\/ACCESS.2019.2942221","article-title":"DHNE: Network representation learning method for dynamic heterogeneous networks","volume":"7","author":"Yin","year":"2019","journal-title":"IEEE Access"},{"key":"2022081612371828100_ref14","first-page":"1","article-title":"Dynamic heterogeneous information network embedding with meta-path based proximity","volume":"4347","author":"Wang","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2022081612371828100_ref15","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1145\/2623330.2623732","volume-title":"Proc. 20th ACM SIGKDD Int. Conf. Knowl. Disc. Data Mining","author":"Perozzi","year":"2014"},{"key":"2022081612371828100_ref16","first-page":"855","volume-title":"Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Disc. Data Mining","author":"Grover","year":"2016"},{"key":"2022081612371828100_ref17","first-page":"891","volume-title":"Proc. 24th ACM Int. Conf. Inf. Knowl. Manag.","author":"Cao","year":"2015"},{"key":"2022081612371828100_ref18","first-page":"1225","volume-title":"Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Disc. Data Mining","author":"Wang","year":"2016"},{"key":"2022081612371828100_ref19","first-page":"1067","volume-title":"Proc. 24th Int. Conf. World Wide Web","author":"Tang","year":"2015"},{"key":"2022081612371828100_ref20","doi-asserted-by":"crossref","first-page":"1373","DOI":"10.1162\/089976603321780317","article-title":"Laplacian eigenmaps for dimensionality reduction and data representation","volume":"15","author":"Belkin","year":"2003","journal-title":"Neural Comput."},{"key":"2022081612371828100_ref21","first-page":"3203","volume-title":"IJCAI","author":"Xue","year":"2017"},{"key":"2022081612371828100_ref22","first-page":"135","volume-title":"Proc. 23rd ACM SIGKDD Int. Conf. Knowl. Disc. Data Mining","author":"Dong","year":"2017"},{"key":"2022081612371828100_ref23","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TKDE.2018.2833443","article-title":"Heterogeneous information network embedding for recommendation","volume":"31","author":"Shi","year":"2018","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2022081612371828100_ref24","first-page":"1797","volume-title":"Proc. ACM Conf. Inf. Knowl. Manag.","author":"Fu","year":"2017"},{"key":"2022081612371828100_ref25","first-page":"1","article-title":"Meta-path guided embedding for similarity search in large-scale heterogeneous information networks","volume":"1610.09769","author":"Shang","year":"2016","journal-title":"arXiv Preprint"},{"key":"2022081612371828100_ref26","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1007\/978-3-319-93037-4_16","volume-title":"Pacific-Asia Conf. Knowl. Disc. Data Mining","author":"Zhang","year":"2018"},{"key":"2022081612371828100_ref27","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1145\/3018661.3018735","volume-title":"Proc. Tenth ACM Int. Conf. Web Search Data Mining","author":"Chen","year":"2017"},{"key":"2022081612371828100_ref28","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1145\/3159652.3159666","volume-title":"Proc. Eleventh ACM Int. Conf. Web Search Data Mining","author":"Wang","year":"2018"},{"key":"2022081612371828100_ref29","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1145\/2783258.2783307","volume-title":"Proc. 21th ACM SIGKDD Int. Conf. Knowl. Disc. Data Mining","author":"Tang","year":"2015"},{"key":"2022081612371828100_ref30","first-page":"1","article-title":"Representation learning over dynamic graphs","volume":"1803.04051","author":"Trivedi","year":"2018","journal-title":"arXiv Preprint"},{"key":"2022081612371828100_ref31","first-page":"387","volume-title":"Proc. 2017 ACM Conf. Inf. Knowl. Manag.","author":"Li","year":"2017"},{"key":"2022081612371828100_ref32","first-page":"2672","volume-title":"Proc. 24th ACM SIGKDD Int. Conf. Knowledge Disc. Data Mining","author":"Yu","year":"2018"},{"key":"2022081612371828100_ref33","first-page":"282","article-title":"Modeling dynamic heterogeneous network for link prediction using hierarchical attention with temporal rnn","volume-title":"Machine Learning and Knowledge Discovery in Databases- European Conference","author":"Xue","year":"2020"},{"key":"2022081612371828100_ref34","article-title":"dyngraph2vec: Capturing network dynamics using dynamic graph representation learning","volume":"187","author":"Goyal","year":"2020","journal-title":"Knowl.-Based Sys."}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/65\/8\/2016\/45329722\/bxab041.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/65\/8\/2016\/45329722\/bxab041.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T12:39:16Z","timestamp":1660653556000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/65\/8\/2016\/6262255"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,3]]},"references-count":34,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,5,3]]},"published-print":{"date-parts":[[2022,8,11]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxab041","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"type":"print","value":"0010-4620"},{"type":"electronic","value":"1460-2067"}],"subject":[],"published-other":{"date-parts":[[2022,8]]},"published":{"date-parts":[[2021,5,3]]}}}