{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:11:57Z","timestamp":1777734717305,"version":"3.51.4"},"reference-count":36,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T00:00:00Z","timestamp":1771200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61661037"],"award-info":[{"award-number":["61661037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62262043"],"award-info":[{"award-number":["62262043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72461026"],"award-info":[{"award-number":["72461026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Complex real-world systems are often modeled as heterogeneous information networks with diverse node and relation types, bringing new opportunities and challenges to link prediction. Traditional methods based on similarity or meta-paths fail to fully capture high-order structures and semantics, while existing hypergraph-based models homogenize all high-order information without considering their importance differences, diluting core associations with redundant noise and limiting prediction accuracy. Given these issues, we propose the VE-HGCN, a link prediction model for HINs that fuses hypergraph convolution with soft-voting ensemble strategy. The model first constructs multiple heterogeneous hypergraphs from HINs via network frequent subgraph pattern extraction, then leverages hypergraph convolution for node representation learning, and finally employs a soft-voting ensemble strategy to fuse multi-model prediction results. Extensive experiments on four public HIN datasets show that the VE-HGCN outperforms seven mainstream baseline models, thereby validating the effectiveness of the proposed method. This study offers a new perspective for link prediction in HINs and exhibits good generality and practicality, providing a feasible reference for addressing high-order information utilization issues in complex heterogeneous network analysis.<\/jats:p>","DOI":"10.3390\/e28020230","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:11:28Z","timestamp":1771240288000},"page":"230","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Link Prediction in Heterogeneous Information Networks: Improved Hypergraph Convolution with Adaptive Soft Voting"],"prefix":"10.3390","volume":"28","author":[{"given":"Sheng","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7733-4758","authenticated-orcid":false,"given":"Yuyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqiang","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangnan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ka","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongmei","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Nanchang Hangkong University, Nanchang 330063, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,16]]},"reference":[{"key":"ref_1","first-page":"2248","article-title":"Semi-Supervised Node Classification in Heterogeneous Networks Based on Hypergraph Convolution","volume":"44","author":"Wu","year":"2021","journal-title":"J. Comput. Sci. Technol."},{"key":"ref_2","first-page":"598","article-title":"A Survey on Heterogeneous Information Network Analysis and Applications","volume":"33","author":"Shi","year":"2022","journal-title":"J. Softw."},{"key":"ref_3","first-page":"4125","article-title":"Heterogeneous Hypergraph Variational Autoencoder for Link Prediction","volume":"44","author":"Fan","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_4","first-page":"2747","article-title":"A Survey on Link Prediction Methods for Heterogeneous Information Networks","volume":"46","author":"Cao","year":"2024","journal-title":"Syst. Eng. Electron."},{"key":"ref_5","unstructured":"Lin, D., and Pantel, P. (2002). An Information-Theoretic Definition of Similarity. Proceedings of the Fifteenth International Conference on Machine Learning, Morgan Kaufmann Publishers Inc."},{"key":"ref_6","first-page":"573","article-title":"Introduction to Modern Information Retrieval","volume":"30","year":"2010","journal-title":"Int. J. Inf. Manag."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"992","DOI":"10.14778\/3402707.3402736","article-title":"PathSim: Meta Path-Based Top-K Similarity Search in Heterogeneous Information Networks","volume":"4","author":"Sun","year":"2011","journal-title":"Proc. VLDB Endow."},{"key":"ref_8","first-page":"651","article-title":"Link Prediction in Complex Networks","volume":"39","author":"Lyu","year":"2010","journal-title":"J. Univ. Electron. Sci. Technol. China"},{"key":"ref_9","first-page":"547","article-title":"\u00c9tude Comparative de La Distribution Florale Dans Une Portion Des Alpes et Des Jura","volume":"37","author":"Jaccard","year":"1901","journal-title":"Bull. De La Soci\u00e9t\u00e9 Vaudoise Des Sci. Nat."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/S0378-8733(03)00009-1","article-title":"Friends and Neighbors on the Web","volume":"25","author":"Adamic","year":"2003","journal-title":"Soc. Netw."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1007\/BF02289026","article-title":"A New Status Index Derived from Sociometric Analysis","volume":"18","author":"Katz","year":"1953","journal-title":"Psychometrika"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"124289","DOI":"10.1016\/j.physa.2020.124289","article-title":"Link Prediction Techniques, Applications, and Performance: A Survey","volume":"553","author":"Kumar","year":"2020","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sun, Y., Han, J., Zhao, P., Yin, Z., Cheng, H., and Wu, T. (2009). RankClus: Integrating Clustering with Ranking for Heterogeneous Information Network Analysis. Proceedings of the 12th International Conference on Extending Database Technology: Advances in Database Technology, ACM.","DOI":"10.1145\/1516360.1516426"},{"key":"ref_14","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":"2017","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_15","first-page":"309","article-title":"Similarity Measurement for Heterogeneous Networks Based on Weighted Fusion of Meta-Paths","volume":"42","author":"Zhao","year":"2021","journal-title":"Comput. Eng. Des."},{"key":"ref_16","first-page":"1947","article-title":"A Link Prediction Method Based on Node Structural Feature Mapping in Large-Scale Networks","volume":"39","author":"Li","year":"2016","journal-title":"J. Comput. Sci. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"128108","DOI":"10.1016\/j.eswa.2025.128108","article-title":"Link Prediction via Robust Bidirectional Deep Nonnegative Matrix Factorization","volume":"287","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1109\/TKDE.2020.2993870","article-title":"Dynamic Heterogeneous Information Network Embedding With Meta-Path Based Proximity","volume":"34","author":"Wang","year":"2022","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_19","first-page":"10167","article-title":"HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs","volume":"32","author":"Yadati","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_20","first-page":"2867","article-title":"Tri-Party Deep Network Representation Learning Using Inductive Matrix Completion","volume":"26","author":"Liu","year":"2019","journal-title":"J. Cent. South Univ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107743","DOI":"10.1016\/j.neunet.2025.107743","article-title":"Path-Aware Multi-Scale Learning for Heterogeneous Graph Neural Network","volume":"191","author":"Fan","year":"2025","journal-title":"Neural Netw."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1038\/s42005-025-02157-3","article-title":"Unveiling the Role of Higher-Order Interactions via Stepwise Reduction","volume":"8","author":"Bian","year":"2025","journal-title":"Commun. Phys."},{"key":"ref_23","first-page":"1","article-title":"A Survey of Hypergraph Application Methods: Problems, Progress, and Challenges","volume":"44","author":"Zeng","year":"2024","journal-title":"J. Comput. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Bretto, A. (2013). Hypergraph Theory: An Introduction\n\t\t\t          , Springer International Publishing. Mathematical Engineering.","DOI":"10.1007\/978-3-319-00080-0"},{"key":"ref_25","first-page":"362","article-title":"A Survey of Hypergraph Neural Networks","volume":"61","author":"Lin","year":"2024","journal-title":"J. Comput. Res. Dev."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Milo, R., Shen-Orr, S., Ltzkovitz, S., Kashtan, N., Chktovskii, D., and Alan, U. (2011). Network Motifs: Simple Building Blocks of Complex Networks. The Structure and Dynamics of Networks, Princeton University Press.","DOI":"10.1515\/9781400841356.217"},{"key":"ref_27","unstructured":"Bruna, J., Zaremba, W., Szlam, A., and LeCun, Y. (2013). Spectral Networks and Locally Connected Networks on Graphs. arXiv."},{"key":"ref_28","unstructured":"Defferrard, M., Bresson, X., and Vandergheynst, P. (2016). Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. arXiv."},{"key":"ref_29","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-Supervised Classification with Graph Convolutional Networks. arXiv."},{"key":"ref_30","first-page":"1601","article-title":"Learning with Hypergraphs: Clustering, Classification, and Embedding","volume":"19","author":"Zhou","year":"2006","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., and Mei, Q. (2015). LINE: Large-scale Information Network Embedding. Proceedings of the 24th International Conference on World Wide Web, ACM.","DOI":"10.1145\/2736277.2741093"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Dong, Y., Chawla, N.V., and Swami, A. (2017). Metapath2vec: Scalable Representation Learning for Heterogeneous Networks. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM.","DOI":"10.1145\/3097983.3098036"},{"key":"ref_33","unstructured":"Sankar, A., Zhang, X., and Chang, K.C.-C. (2019). Motif-Based Convolutional Neural Network on Graphs. arXiv."},{"key":"ref_34","unstructured":"Wang, X., Ji, H., Shi, C., Wang, B., Cui, P., Yu, P., and Ye, Y. (2021). Heterogeneous Graph Attention Network. arXiv."},{"key":"ref_35","unstructured":"Wang, Y., Zhang, Y., Liu, Y., and Chen, H. (2024). Heterogeneous Graph Contrastive Learning for Recommendation. Proceedings of the ACM Web Conference 2024, ACM."},{"key":"ref_36","first-page":"8756","article-title":"Interaction-aware Enhanced Heterogeneous Graph Convolutional Network","volume":"Volume 38","author":"Li","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/2\/230\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:14:45Z","timestamp":1771240485000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/2\/230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,16]]},"references-count":36,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["e28020230"],"URL":"https:\/\/doi.org\/10.3390\/e28020230","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,16]]}}}