{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T08:55:09Z","timestamp":1789548909267,"version":"build-2803163510"},"reference-count":86,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.knosys.2026.116595","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:22:23Z","timestamp":1783437743000},"page":"116595","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PA","title":["Are heterogeneous graph neural networks truly effective for node classification? A causal perspective"],"prefix":"10.1016","volume":"351","author":[{"given":"Xiao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejiao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7626-7295","authenticated-orcid":false,"given":"Zhiqi","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.knosys.2026.116595_b1","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"2","key":"10.1016\/j.knosys.2026.116595_b2","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/TAI.2021.3076021","article-title":"Graph learning: A survey","volume":"2","author":"Xia","year":"2021","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116595_b3","doi-asserted-by":"crossref","unstructured":"Y. Bei, W. Chen, H. Chen, S. Zhou, C. Yang, J. Fan, L. Huang, J. Bu, Correlation-aware graph convolutional networks for multi-label node classification, in: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 1, 2025, pp. 37\u201348.","DOI":"10.1145\/3690624.3709197"},{"key":"10.1016\/j.knosys.2026.116595_b4","article-title":"A unified gradient regularization method for heterogeneous graph neural networks","author":"Yang","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.knosys.2026.116595_b5","series-title":"Gc4nc: A benchmark framework for graph condensation on node classification with new insights","author":"Gong","year":"2024"},{"issue":"8","key":"10.1016\/j.knosys.2026.116595_b6","doi-asserted-by":"crossref","first-page":"4386","DOI":"10.1109\/TNNLS.2021.3113026","article-title":"Brain-inspired search engine assistant based on knowledge graph","volume":"34","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.knosys.2026.116595_b7","series-title":"A binary classification social network dataset for graph machine learning","author":"Ali","year":"2025"},{"key":"10.1016\/j.knosys.2026.116595_b8","first-page":"4136","article-title":"Cross-layer and cross-sample feature optimization network for few-shot fine-grained image classification","volume":"vol. 38, no. 5","author":"Ma","year":"2024"},{"issue":"10","key":"10.1016\/j.knosys.2026.116595_b9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3661821","article-title":"A survey of graph neural networks for social recommender systems","volume":"56","author":"Sharma","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.knosys.2026.116595_b10","series-title":"2018 IEEE International Conference on Software Maintenance and Evolution","first-page":"183","article-title":"Improving api caveats accessibility by mining api caveats knowledge graph","author":"Li","year":"2018"},{"key":"10.1016\/j.knosys.2026.116595_b11","first-page":"22001","article-title":"A generalizable anomaly detection method in dynamic graphs","volume":"vol. 39, no. 20","author":"Yang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116595_b12","series-title":"Identifying evidence subgraphs for financial risk detection via graph counterfactual and factual reasoning","author":"Du","year":"2025"},{"key":"10.1016\/j.knosys.2026.116595_b13","doi-asserted-by":"crossref","unstructured":"X. Zhao, S. Liu, S.-Y. Yang, C. Miao, Medrag: Enhancing retrieval-augmented generation with knowledge graph-elicited reasoning for healthcare copilot, in: Proceedings of the ACM on Web Conference 2025, 2025, pp. 4442\u20134457.","DOI":"10.1145\/3696410.3714782"},{"key":"10.1016\/j.knosys.2026.116595_b14","series-title":"A smart multimodal healthcare copilot with powerful llm reasoning","author":"Zhao","year":"2025"},{"key":"10.1016\/j.knosys.2026.116595_b15","doi-asserted-by":"crossref","unstructured":"X. Yang, X. Zhao, Z. Shen, EHRStruct: A Comprehensive Benchmark Framework for Evaluating Large Language Models on Structured Electronic Health Record Tasks, in: Proceedings of the AAAI Conference on Artificial Intelligence, 40, (40) 2026, pp. 34340\u201334348.","DOI":"10.1609\/aaai.v40i40.40731"},{"issue":"7","key":"10.1016\/j.knosys.2026.116595_b16","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-024-4457-2","article-title":"Molecular pretraining models towards molecular property prediction","volume":"68","author":"Qiao","year":"2025","journal-title":"Sci. China Inf. Sci."},{"issue":"1","key":"10.1016\/j.knosys.2026.116595_b17","doi-asserted-by":"crossref","first-page":"4382","DOI":"10.1038\/s41467-025-59634-0","article-title":"A self-conformation-aware pre-training framework for molecular property prediction with substructure interpretability","volume":"16","author":"Qiao","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.knosys.2026.116595_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113699","article-title":"Msn-dta: a multi-scale node adaptive graph neural network for interpretable drug-target binding affinity prediction","volume":"320","author":"Wang","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"20","key":"10.1016\/j.knosys.2026.116595_b19","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"Stat"},{"key":"10.1016\/j.knosys.2026.116595_b20","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116595_b21","series-title":"Explainable Q&A System Based on Domain-Specific Knowledge Graph","author":"Zhao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116595_b22","series-title":"International Conference on Machine Learning","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"issue":"1","key":"10.1016\/j.knosys.2026.116595_b23","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/TKDE.2016.2598561","article-title":"A survey of heterogeneous information network analysis","volume":"29","author":"Shi","year":"2016","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"10","key":"10.1016\/j.knosys.2026.116595_b24","doi-asserted-by":"crossref","first-page":"4854","DOI":"10.1109\/TKDE.2020.3045924","article-title":"Heterogeneous network representation learning: A unified framework with survey and benchmark","volume":"34","author":"Yang","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116595_b25","doi-asserted-by":"crossref","unstructured":"C. Zhang, D. Song, C. Huang, A. Swami, N.V. Chawla, Heterogeneous graph neural network, in: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 793\u2013803.","DOI":"10.1145\/3292500.3330961"},{"issue":"2","key":"10.1016\/j.knosys.2026.116595_b26","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1109\/TBDATA.2022.3177455","article-title":"A survey on heterogeneous graph embedding: methods, techniques, applications and sources","volume":"9","author":"Wang","year":"2022","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.knosys.2026.116595_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2026.116549","article-title":"Predicting international coalition formation with relational graph neural networks: a temporal heterogeneous approach with rich pooling","author":"Kutsal","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116595_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112644","article-title":"Dual de-confounded causal intervention method for knowledge graph error detection","volume":"305","author":"Yang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116595_b29","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2025.3528461","article-title":"Llm-driven causal discovery via harmonized prior","author":"Ban","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116595_b30","article-title":"A causal adversarial graph neural network for multi-center autism spectrum disorder identification","author":"Zhang","year":"2026","journal-title":"Knowl.-Based Syst."},{"issue":"2","key":"10.1016\/j.knosys.2026.116595_b31","doi-asserted-by":"crossref","first-page":"80","DOI":"10.26599\/IJCS.2022.9100013","article-title":"Link prediction in continuous-time dynamic heterogeneous graphs with causality of event types","volume":"6","author":"Zhu","year":"2022","journal-title":"Int. J. Crowd Sci."},{"key":"10.1016\/j.knosys.2026.116595_b32","doi-asserted-by":"crossref","unstructured":"B. Jing, D. Zhou, K. Ren, C. Yang, Causality-aware spatiotemporal graph neural networks for spatiotemporal time series imputation, in: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024, pp. 1027\u20131037.","DOI":"10.1145\/3627673.3679642"},{"issue":"4","key":"10.1016\/j.knosys.2026.116595_b33","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s10994-024-06729-2","article-title":"Inferring individual direct causal effects under heterogeneous peer influence","volume":"114","author":"Adhikari","year":"2025","journal-title":"Mach. Learn."},{"issue":"8","key":"10.1016\/j.knosys.2026.116595_b34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3673761","article-title":"Learning individual treatment effects under heterogeneous interference in networks","volume":"18","author":"Zhao","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.1016\/j.knosys.2026.116595_b35","series-title":"Estimating heterogeneous causal effect on networks via orthogonal learning","author":"Wu","year":"2025"},{"key":"10.1016\/j.knosys.2026.116595_b36","doi-asserted-by":"crossref","unstructured":"Q. Lv, M. Ding, Q. Liu, Y. Chen, W. Feng, S. He, C. Zhou, J. Jiang, Y. Dong, J. Tang, Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks, in: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, pp. 1150\u20131160.","DOI":"10.1145\/3447548.3467350"},{"key":"10.1016\/j.knosys.2026.116595_b37","series-title":"Classic GNNs are strong baselines: Reassessing GNNs for node classification","author":"Luo","year":"2024"},{"key":"10.1016\/j.knosys.2026.116595_b38","series-title":"The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3\u20137, 2018, Proceedings 15","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018"},{"key":"10.1016\/j.knosys.2026.116595_b39","series-title":"Is homophily a necessity for graph neural networks?","author":"Ma","year":"2021"},{"key":"10.1016\/j.knosys.2026.116595_b40","first-page":"7793","article-title":"Beyond homophily in graph neural networks: Current limitations and effective designs","volume":"33","author":"Zhu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116595_b41","article-title":"When do graph neural networks help with node classification? investigating the homophily principle on node distinguishability","volume":"36","author":"Luan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116595_b42","doi-asserted-by":"crossref","first-page":"65823","DOI":"10.52202\/079017-2104","article-title":"On the impact of feature heterophily on link prediction with graph neural networks","volume":"37","author":"Zhu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116595_b43","series-title":"Node-wise localization of graph neural networks","author":"Liu","year":"2021"},{"key":"10.1016\/j.knosys.2026.116595_b44","series-title":"International Conference on Machine Learning","first-page":"11975","article-title":"From local structures to size generalization in graph neural networks","author":"Yehudai","year":"2021"},{"key":"10.1016\/j.knosys.2026.116595_b45","series-title":"Learning on Graphs Conference","first-page":"6:1","article-title":"On performance discrepancies across local homophily levels in graph neural networks","author":"Loveland","year":"2024"},{"key":"10.1016\/j.knosys.2026.116595_b46","doi-asserted-by":"crossref","unstructured":"Z. Hu, Y. Dong, K. Wang, Y. Sun, Heterogeneous graph transformer, in: Proceedings of the Web Conference 2020, 2020, pp. 2704\u20132710.","DOI":"10.1145\/3366423.3380027"},{"key":"10.1016\/j.knosys.2026.116595_b47","doi-asserted-by":"crossref","unstructured":"X. Wang, H. Ji, C. Shi, B. Wang, Y. Ye, P. Cui, P.S. Yu, Heterogeneous graph attention network, in: The World Wide Web Conference, 2019, pp. 2022\u20132032.","DOI":"10.1145\/3308558.3313562"},{"key":"10.1016\/j.knosys.2026.116595_b48","doi-asserted-by":"crossref","unstructured":"X. Fu, J. Zhang, Z. Meng, I. King, Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding, in: Proceedings of the Web Conference 2020, 2020, pp. 2331\u20132341.","DOI":"10.1145\/3366423.3380297"},{"key":"10.1016\/j.knosys.2026.116595_b49","article-title":"Graph transformer networks","volume":"32","author":"Yun","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116595_b50","doi-asserted-by":"crossref","unstructured":"J. Zhao, X. Wang, C. Shi, Z. Liu, Y. Ye, Network schema preserving heterogeneous information network embedding, in: International Joint Conference on Artificial Intelligence, IJCAI, 2020.","DOI":"10.24963\/ijcai.2020\/190"},{"key":"10.1016\/j.knosys.2026.116595_b51","doi-asserted-by":"crossref","unstructured":"Q. Mao, Z. Liu, C. Liu, J. Sun, Hinormer: Representation learning on heterogeneous information networks with graph transformer, in: Proceedings of the ACM Web Conference 2023, 2023, pp. 599\u2013610.","DOI":"10.1145\/3543507.3583493"},{"key":"10.1016\/j.knosys.2026.116595_b52","first-page":"10816","article-title":"Simple and efficient heterogeneous graph neural network","volume":"vol. 37, no. 9","author":"Yang","year":"2023"},{"issue":"5","key":"10.1016\/j.knosys.2026.116595_b53","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1037\/h0037350","article-title":"Estimating causal effects of treatments in randomized and nonrandomized studies","volume":"66","author":"Rubin","year":"1974","journal-title":"J. Educ. Psychol."},{"key":"10.1016\/j.knosys.2026.116595_b54","series-title":"The Neyman\u2014Rubin model of causal inference and estimation via matching methods","author":"Sekhon","year":"2008"},{"issue":"2276","key":"10.1016\/j.knosys.2026.116595_b55","doi-asserted-by":"crossref","DOI":"10.1098\/rspa.2023.0121","article-title":"Causal lifting and link prediction","volume":"479","author":"Cotta","year":"2023","journal-title":"Proc. R. Soc. A"},{"key":"10.1016\/j.knosys.2026.116595_b56","doi-asserted-by":"crossref","unstructured":"G. Chen, Y. Wang, F. Guo, Q. Guo, J. Shao, H. Shen, X. Cheng, Causality and independence enhancement for biased node classification, in: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023, pp. 203\u2013212.","DOI":"10.1145\/3583780.3614804"},{"key":"10.1016\/j.knosys.2026.116595_b57","series-title":"CEGRL-TKGR: A causal enhanced graph representation learning framework for temporal knowledge graph reasoning","author":"Sun","year":"2024"},{"key":"10.1016\/j.knosys.2026.116595_b58","doi-asserted-by":"crossref","unstructured":"S. Jiang, Y. Sun, Estimating causal effects on networked observational data via representation learning, in: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022, pp. 852\u2013861.","DOI":"10.1145\/3511808.3557311"},{"key":"10.1016\/j.knosys.2026.116595_b59","series-title":"Estimating peer direct and indirect effects in observational network data","author":"Du","year":"2024"},{"key":"10.1016\/j.knosys.2026.116595_b60","series-title":"Forty-First International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","article-title":"From geometry to causality- Ricci curvature and the reliability of causal inference on networks","author":"Farzam","year":"2024"},{"key":"10.1016\/j.knosys.2026.116595_b61","doi-asserted-by":"crossref","unstructured":"R. Cai, Z. Yang, W. Chen, Y. Yan, Z. Hao, Generalization bound for estimating causal effects from observational network data, in: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 2023, pp. 163\u2013172.","DOI":"10.1145\/3583780.3614892"},{"key":"10.1016\/j.knosys.2026.116595_b62","doi-asserted-by":"crossref","unstructured":"B. Hu, Z. An, Z. Wu, K. Tu, Z. Liu, Z. Zhang, J. Zhou, Y. Feng, J. Chen, Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data, in: Proceedings of the Eighteenth ACM International Conference on Web Search and Data Mining, 2025, pp. 1\u20139.","DOI":"10.1145\/3701551.3703525"},{"key":"10.1016\/j.knosys.2026.116595_b63","doi-asserted-by":"crossref","unstructured":"Y. Sui, C. Tang, Z. Chu, J. Fang, Y. Gao, Q. Cui, L. Li, J. Zhou, X. Wang, Invariant graph learning for causal effect estimation, in: Proceedings of the ACM Web Conference 2024, 2024, pp. 2552\u20132562.","DOI":"10.1145\/3589334.3645549"},{"key":"10.1016\/j.knosys.2026.116595_b64","article-title":"Large-scale hierarchical causal discovery via weak prior knowledge","author":"Wang","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116595_b65","doi-asserted-by":"crossref","DOI":"10.1109\/TETCI.2025.3540429","article-title":"Harnessing the power of knowledge graphs to improve causal discovery","author":"Ban","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"10.1016\/j.knosys.2026.116595_b66","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112859","article-title":"Dynamic network security leveraging efficient CoviNet with granger causality-inspired graph neural networks for data compression in cloud IoT devices","volume":"309","author":"Begum","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116595_b67","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111592","article-title":"Introducing diminutive causal structure into graph representation learning","volume":"293","author":"Gao","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116595_b68","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111913","article-title":"A graph-based approach for traffic prediction using similarity and causal relations between nodes","volume":"296","author":"Khaled","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116595_b69","doi-asserted-by":"crossref","unstructured":"H. Han, T. Zhao, C. Yang, H. Zhang, Y. Liu, X. Wang, C. Shi, Openhgnn: an open source toolkit for heterogeneous graph neural network, in: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, 2022, pp. 3993\u20133997.","DOI":"10.1145\/3511808.3557664"},{"key":"10.1016\/j.knosys.2026.116595_b70","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.knosys.2026.116595_b71","series-title":"2019 IEEE International Conference on Data Mining","first-page":"1534","article-title":"Relation structure-aware heterogeneous graph neural network","author":"Zhu","year":"2019"},{"key":"10.1016\/j.knosys.2026.116595_b72","doi-asserted-by":"crossref","unstructured":"P. Yu, C. Fu, Y. Yu, C. Huang, Z. Zhao, J. Dong, Multiplex heterogeneous graph convolutional network, in: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 2377\u20132387.","DOI":"10.1145\/3534678.3539482"},{"key":"10.1016\/j.knosys.2026.116595_b73","series-title":"International Conference on Machine Learning","first-page":"42644","article-title":"SlotGAT: slot-based message passing for heterogeneous graphs","author":"Zhou","year":"2023"},{"key":"10.1016\/j.knosys.2026.116595_b74","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2024.3434956","article-title":"Efficient heterogeneous graph learning via random projection","author":"Hu","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116595_b75","unstructured":"Y. Mo, F. Nie, P. Hu, H.T. Shen, Z. Zhang, X. Wang, X. Zhu, Self-Supervised Heterogeneous Graph Learning: a Homophily and Heterogeneity View, in: The Twelfth International Conference on Learning Representations."},{"key":"10.1016\/j.knosys.2026.116595_b76","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2021.101447","article-title":"Heterogeneous star graph attention network for product attributes prediction","volume":"51","author":"Zhao","year":"2022","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.knosys.2026.116595_b77","first-page":"4132","article-title":"An attention-based graph neural network for heterogeneous structural learning","volume":"vol. 34, no. 04","author":"Hong","year":"2020"},{"key":"10.1016\/j.knosys.2026.116595_b78","doi-asserted-by":"crossref","unstructured":"X. Wang, N. Liu, H. Han, C. Shi, Self-supervised heterogeneous graph neural network with co-contrastive learning, in: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021, pp. 1726\u20131736.","DOI":"10.1145\/3447548.3467415"},{"key":"10.1016\/j.knosys.2026.116595_b79","series-title":"2021 IEEE 37th International Conference on Data Engineering","first-page":"912","article-title":"Leveraging meta-path contexts for classification in heterogeneous information networks","author":"Li","year":"2021"},{"key":"10.1016\/j.knosys.2026.116595_b80","first-page":"4697","article-title":"Heterogeneous graph structure learning for graph neural networks","volume":"vol. 35, no. 5","author":"Zhao","year":"2021"},{"key":"10.1016\/j.knosys.2026.116595_b81","doi-asserted-by":"crossref","unstructured":"J. Guo, L. Du, W. Bi, Q. Fu, X. Ma, X. Chen, S. Han, D. Zhang, Y. Zhang, Homophily-oriented heterogeneous graph rewiring, in: Proceedings of the ACM Web Conference 2023, 2023, pp. 511\u2013522.","DOI":"10.1145\/3543507.3583454"},{"key":"10.1016\/j.knosys.2026.116595_b82","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 Netw."},{"key":"10.1016\/j.knosys.2026.116595_b83","series-title":"Heterogeneous Graph Transformer with Poly-Tokenization","author":"Lu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116595_b84","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122404","article-title":"Higher order heterogeneous graph neural network based on node attribute enhancement","volume":"238","author":"Li","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116595_b85","first-page":"5371","article-title":"Unsupervised attributed multiplex network embedding","volume":"vol. 34, no. 04","author":"Park","year":"2020"},{"key":"10.1016\/j.knosys.2026.116595_b86","doi-asserted-by":"crossref","unstructured":"Q. Chen, G. Song, Adaptive heterogeneous graph neural networks: Bridging heterophily and heterogeneity, in: Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025, pp. 312\u2013321.","DOI":"10.1145\/3746252.3761131"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126013213?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126013213?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T14:45:36Z","timestamp":1789310736000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126013213"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":86,"alternative-id":["S0950705126013213"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116595","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Are heterogeneous graph neural networks truly effective for node classification? A causal perspective","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116595","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116595"}}