{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T15:28:31Z","timestamp":1786807711902,"version":"3.56.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["E3KF461001"],"award-info":[{"award-number":["E3KF461001"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["22BTJ011"],"award-info":[{"award-number":["22BTJ011"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132665","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:52:57Z","timestamp":1777571577000},"page":"132665","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["CHMA-Net : Contrastive triplet networks for heterogeneous graph representation learning with multiscale augmentation"],"prefix":"10.1016","volume":"325","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3805-8201","authenticated-orcid":false,"given":"Xiuli","family":"Xiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2442-3679","authenticated-orcid":false,"given":"Huanhuan","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9045-5158","authenticated-orcid":false,"given":"Xuchu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6935-5470","authenticated-orcid":false,"given":"Zonggao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132665_bib0001","series-title":"The eleventh international conference on learning representations","article-title":"SpecFormer: Spectral graph neural networks meet transformers","author":"Bo","year":"2023"},{"key":"10.1016\/j.eswa.2026.132665_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110182","article-title":"Improving augmentation consistency for graph contrastive learning","volume":"148","author":"Bu","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132665_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.110182","article-title":"Improving augmentation consistency for graph contrastive learning","volume":"148","author":"Bu","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132665_bib0004","first-page":"8037","article-title":"GCCAD: Graph contrastive coding for anomaly detection","volume":"35","author":"Chen","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.132665_bib0005","series-title":"Proceedings of the 30th ACM SIGKDD Conference on knowledge discovery and data mining","first-page":"689","article-title":"Reserving-masking-reconstruction model for self-supervised heterogeneous graph representation","author":"Duan","year":"2024"},{"key":"10.1016\/j.eswa.2026.132665_bib0006","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.neunet.2023.11.030","article-title":"MECCH: Metapath context convolution-based heterogeneous graph neural networks","volume":"170","author":"Fu","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.132665_bib0007","series-title":"Proceedings of the web conference 2020","first-page":"2331","article-title":"MAGNN: Metapath aggregated graph neural network for heterogeneous graph embedding","author":"Fu","year":"2020"},{"key":"10.1016\/j.eswa.2026.132665_bib0008","series-title":"Thirty-fourth annual conference on neural information processing systems","article-title":"GraphCL: Contrastive self-supervised learning of graph representations","author":"Hafidi","year":"2020"},{"key":"10.1016\/j.eswa.2026.132665_bib0009","series-title":"Proceedings of the 37th International conference on machine learning","first-page":"4116","article-title":"Contrastive multi-view representation learning on graphs","author":"Hassani","year":"2020"},{"key":"10.1016\/j.eswa.2026.132665_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113608","article-title":"Multi-scale sub-graph view generation and siamese contrastive learning for graph representations","volume":"182","author":"Hong","year":"2025","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.eswa.2026.132665_bib0011","series-title":"Proceedings of the web conference 2020","first-page":"2704","article-title":"Heterogeneous graph transformer","author":"Hu","year":"2020"},{"key":"10.1016\/j.eswa.2026.132665_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111618","article-title":"Node classification oriented adaptive multichannel heterogeneous graph neural network","volume":"292","author":"Li","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132665_bib0013","series-title":"Proceedings of the thirty-seventh AAAI Conference on artificial intelligence","first-page":"4516","article-title":"Beyond smoothing: Unsupervised graph representation learning with edge heterophily discriminating","author":"Liu","year":"2023"},{"key":"10.1016\/j.eswa.2026.132665_bib0014","doi-asserted-by":"crossref","first-page":"4411","DOI":"10.1007\/s10489-024-05363-8","article-title":"Heterogeneous graph neural network with graph-data augmentation and adaptive denoising","volume":"54","author":"Lou","year":"2024","journal-title":"Applied Intelligence"},{"key":"10.1016\/j.eswa.2026.132665_bib0015","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1109\/TNNLS.2022.3177775","article-title":"CLEAR: Cluster-enhanced contrast for self-supervised graph representation learning","volume":"35","author":"Luo","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132665_bib0016","series-title":"Advances in neural information processing systems","first-page":"43133","article-title":"Revisiting self-supervised heterogeneous graph learning from spectral clustering perspective","volume":"vol. 37","author":"Mo","year":"2024"},{"key":"10.1016\/j.eswa.2026.132665_bib0017","series-title":"The twelfth international conference on learning representations","article-title":"Self-supervised heterogeneous graph learning: A homophily and heterogeneity view","author":"Mo","year":"2024"},{"key":"10.1016\/j.eswa.2026.132665_bib0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126751","article-title":"Two-level attention mechanism with contrastive learning for heterogeneous graph representation learning","volume":"273","author":"Moradi","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132665_bib0019","doi-asserted-by":"crossref","first-page":"11476","DOI":"10.1109\/TKDE.2022.3224193","article-title":"Heterogeneous graph neural network with multi-view representation learning","volume":"35","author":"Shao","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.132665_bib0020","doi-asserted-by":"crossref","first-page":"10283","DOI":"10.1109\/TNNLS.2025.3540063","article-title":"When heterophily meets heterogeneous graphs: Latent graphs guided unsupervised representation learning","volume":"36","author":"Shen","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132665_bib0021","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106645","article-title":"GTC: GNN-transformer co-contrastive learning for self-supervised heterogeneous graph representation","volume":"181","author":"Sun","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.eswa.2026.132665_bib0022","first-page":"809","article-title":"Reliability-driven local community search in dynamic networks","volume":"36","author":"Tang","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.132665_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131233","article-title":"Dual intent-aware contrastive learning on heterogeneous information networks for recommendation","volume":"309","author":"Tang","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132665_bib0024","series-title":"Proceedings of the AAAI Conference on artificial intelligence","first-page":"9997","article-title":"Heterogeneous graph masked autoencoders","volume":"vol. 37","author":"Tian","year":"2023"},{"key":"10.1016\/j.eswa.2026.132665_bib0025","series-title":"6th International conference on learning representations","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"10.1016\/j.eswa.2026.132665_bib0026","series-title":"International conference on learning representations","article-title":"Deep graph infomax","author":"Veli\u010dkovi\u0107","year":"2019"},{"key":"10.1016\/j.eswa.2026.132665_bib0027","doi-asserted-by":"crossref","first-page":"10981","DOI":"10.1109\/TKDE.2022.3233481","article-title":"A multi-type transferable method for missing link prediction in heterogeneous social networks","volume":"35","author":"Wang","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.132665_bib0028","series-title":"The world wide web conference","first-page":"2022","article-title":"Heterogeneous graph attention network","author":"Wang","year":"2019"},{"key":"10.1016\/j.eswa.2026.132665_bib0029","series-title":"The 27th ACM SIGKDD Conference on knowledge discovery and data mining","article-title":"Self-supervised heterogeneous graph neural network with co-contrastive learning","author":"Wang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132665_bib0030","series-title":"Proceedings of the 2023\u202fSIAM International conference on data mining","first-page":"136","article-title":"Heterogeneous graph contrastive multi-view learning","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132665_bib0031","doi-asserted-by":"crossref","first-page":"12358","DOI":"10.1109\/TNNLS.2023.3257325","article-title":"Homophily-enhanced self-supervision for graph structure learning: Insights and directions","volume":"35","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132665_bib0032","doi-asserted-by":"crossref","first-page":"3483","DOI":"10.1007\/s11280-023-01194-8","article-title":"Course map learning with graph convolutional network based on AuCM","volume":"26","author":"Xia","year":"2023","journal-title":"World Wide Web"},{"key":"10.1016\/j.eswa.2026.132665_bib0033","doi-asserted-by":"crossref","first-page":"2054","DOI":"10.1109\/TNNLS.2022.3186512","article-title":"Interpolation-based contrastive learning for few-label semi-supervised learning","volume":"35","author":"Yang","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.132665_bib0034","series-title":"Proceedings of the 2016 Conference of the North American chapter of the association for computational linguistics: Human language technologies","first-page":"1480","article-title":"Hierarchical attention networks for document classification","author":"Yang","year":"2016"},{"key":"10.1016\/j.eswa.2026.132665_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112748","article-title":"ConUMIP: Continuous-time dynamic graph learning via uncertainty masked mix-up on representation space","volume":"306","author":"Zhang","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132665_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111052","article-title":"IMCSN: An improved neighborhood aggregation interaction strategy for multi-scale contrastive siamese networks","volume":"158","author":"Zhang","year":"2025","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132665_bib0037","article-title":"Heterogeneous graph contrastive learning with spectral augmentation and dual aggregation","volume":"172","author":"Zhang","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.eswa.2026.132665_bib0038","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130173","article-title":"Hierarchical cross-view contrastive learning for heterogeneous graph","volume":"299","author":"Zhang","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132665_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2025.113056","article-title":"Multi-view self-supervised learning on heterogeneous graphs for recommendation","volume":"174","author":"Zhang","year":"2025","journal-title":"Applied Soft Computing"},{"key":"10.1016\/j.eswa.2026.132665_bib0040","series-title":"Proceedings of the AAAI Conference on artificial intelligence","first-page":"11289","article-title":"Spectral feature augmentation for graph contrastive learning and beyond","volume":"vol. 37","author":"Zhang","year":"2023"},{"issue":"10","key":"10.1016\/j.eswa.2026.132665_bib0041","doi-asserted-by":"crossref","first-page":"5100","DOI":"10.1109\/TAI.2024.3400751","article-title":"Heterogeneous graph contrastive learning with augmentation graph","volume":"5","author":"Zhao","year":"2024","journal-title":"IEEE Transactions on Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.132665_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113845","article-title":"Dynamic graph contrastive learning based on learnable view generators","volume":"324","author":"Zhu","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132665_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130896","article-title":"CTHNE: Contrastive triplet learning for heterogeneous information networks with enhanced model fusion","volume":"650","author":"Zhu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132665_bib0044","series-title":"The thirty-seventh international conference on machine learning","article-title":"Deep graph contrastive representation learning","author":"Zhu","year":"2020"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426015782?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426015782?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T15:10:48Z","timestamp":1786806648000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426015782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":44,"alternative-id":["S0957417426015782"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132665","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"CHMA-Net : Contrastive triplet networks for heterogeneous graph representation learning with multiscale augmentation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132665","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132665"}}