{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:00:38Z","timestamp":1781006438050,"version":"3.54.1"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.116092","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:10:07Z","timestamp":1777569007000},"page":"116092","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Importance-guided neighborhood aggregation for link prediction via adaptive link representation"],"prefix":"10.1016","volume":"345","author":[{"given":"Jiayu","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8425-9954","authenticated-orcid":false,"given":"Darong","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116092_b1","first-page":"17009","article-title":"Design space for graph neural networks","volume":"33","author":"You","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.knosys.2026.116092_b2","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."},{"key":"10.1016\/j.knosys.2026.116092_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jnca.2020.102716","article-title":"Applications of link prediction in social networks: A review","volume":"166","author":"Daud","year":"2020","journal-title":"J. Netw. Comput. Appl."},{"key":"10.1016\/j.knosys.2026.116092_b4","doi-asserted-by":"crossref","unstructured":"Z. Huang, X. Li, H. Chen, Link prediction approach to collaborative filtering, in: Proceedings of the 5th ACM\/IEEE-CS Joint Conference on Digital Libraries, 2005, pp. 141\u2013142.","DOI":"10.1145\/1065385.1065415"},{"issue":"3","key":"10.1016\/j.knosys.2026.116092_b5","doi-asserted-by":"crossref","DOI":"10.3390\/sym13030485","article-title":"A survey on knowledge graph embeddings for link prediction","volume":"13","author":"Wang","year":"2021","journal-title":"Symmetry"},{"key":"10.1016\/j.knosys.2026.116092_b6","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.knosys.2026.116092_b7","series-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"10.1016\/j.knosys.2026.116092_b8","first-page":"9061","article-title":"Labeling trick: A theory of using graph neural networks for multi-node representation learning","volume":"34","author":"Zhang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116092_b9","series-title":"On the equivalence between positional node embeddings and structural graph representations","author":"Srinivasan","year":"2019"},{"key":"10.1016\/j.knosys.2026.116092_b10","doi-asserted-by":"crossref","unstructured":"C. Morris, M. Ritzert, M. Fey, W.L. Hamilton, J.E. Lenssen, G. Rattan, M. Grohe, Weisfeiler and leman go neural: Higher-order graph neural networks, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, 2019, pp. 4602\u20134609.","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"10.1016\/j.knosys.2026.116092_b11","first-page":"13683","article-title":"Neo-gnns: Neighborhood overlap-aware graph neural networks for link prediction","volume":"34","author":"Yun","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116092_b12","series-title":"Graph neural networks for link prediction with subgraph sketching","author":"Chamberlain","year":"2023"},{"key":"10.1016\/j.knosys.2026.116092_b13","first-page":"73000","article-title":"Pure message passing can estimate common neighbor for link prediction","volume":"37","author":"Dong","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116092_b14","doi-asserted-by":"crossref","unstructured":"H. Shomer, Y. Ma, H. Mao, J. Li, B. Wu, J. Tang, LPFormer: An adaptive graph transformer for link prediction, in: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2024, pp. 2686\u20132698.","DOI":"10.1145\/3637528.3672025"},{"key":"10.1016\/j.knosys.2026.116092_b15","series-title":"Neural common neighbor with completion for link prediction","author":"Wang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116092_b16","series-title":"Revisiting link prediction: A data perspective","author":"Mao","year":"2023"},{"issue":"43","key":"10.1016\/j.knosys.2026.116092_b17","first-page":"1","article-title":"Benchmarking graph neural networks","volume":"24","author":"Dwivedi","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116092_b18","doi-asserted-by":"crossref","first-page":"3853","DOI":"10.52202\/075280-0169","article-title":"Evaluating graph neural networks for link prediction: Current pitfalls and new benchmarking","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116092_b19","series-title":"Mixture of link predictors","author":"Ma","year":"2024"},{"key":"10.1016\/j.knosys.2026.116092_b20","series-title":"On the bottleneck of graph neural networks and its practical implications","author":"Alon","year":"2020"},{"key":"10.1016\/j.knosys.2026.116092_b21","series-title":"Understanding over-squashing and bottlenecks on graphs via curvature","author":"Topping","year":"2021"},{"key":"10.1016\/j.knosys.2026.116092_b22","series-title":"Not all neighbors are worth attending to: Graph selective attention networks for semi-supervised learning","author":"He","year":"2022"},{"key":"10.1016\/j.knosys.2026.116092_b23","doi-asserted-by":"crossref","unstructured":"D. Liben-Nowell, J. Kleinberg, The link prediction problem for social networks, in: Proceedings of the Twelfth International Conference on Information and Knowledge Management, 2003, pp. 556\u2013559.","DOI":"10.1145\/956863.956972"},{"key":"10.1016\/j.knosys.2026.116092_b24","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.2026.116092_b25","series-title":"How attentive are graph attention networks?","author":"Brody","year":"2021"},{"key":"10.1016\/j.knosys.2026.116092_b26","series-title":"Graph-bert: Only attention is needed for learning graph representations","author":"Zhang","year":"2020"},{"key":"10.1016\/j.knosys.2026.116092_b27","series-title":"A topological perspective on demystifying gnn-based link prediction performance","author":"Wang","year":"2023"},{"key":"10.1016\/j.knosys.2026.116092_b28","doi-asserted-by":"crossref","unstructured":"L. Shi, B. Hu, D. Zhao, J. He, Z. Zhang, J. Zhou, Structural information enhanced graph representation for link prediction, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, 2024, pp. 14964\u201314972.","DOI":"10.1609\/aaai.v38i13.29417"},{"key":"10.1016\/j.knosys.2026.116092_b29","series-title":"Learning on Graphs Conference","first-page":"38:1","article-title":"Rethinking higher-order representation learning with graph neural networks","volume":"vol. 231","author":"Xu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116092_b30","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.2026.116092_b31","series-title":"International Conference on Machine Learning","first-page":"21","article-title":"Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing","author":"Abu-El-Haija","year":"2019"},{"key":"10.1016\/j.knosys.2026.116092_b32","series-title":"Revisiting semi-supervised learning with graph embeddings","author":"Yang","year":"2016"},{"key":"10.1016\/j.knosys.2026.116092_b33","series-title":"Pitfalls of graph neural network evaluation","author":"Shchur","year":"2018"},{"issue":"2","key":"10.1016\/j.knosys.2026.116092_b34","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.64.025102","article-title":"Clustering and preferential attachment in growing networks","volume":"64","author":"Newman","year":"2001","journal-title":"Phys. Rev. E"},{"issue":"3","key":"10.1016\/j.knosys.2026.116092_b35","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":"10.1016\/j.knosys.2026.116092_b36","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1140\/epjb\/e2009-00335-8","article-title":"Predicting missing links via local information","volume":"71","author":"Zhou","year":"2009","journal-title":"Eur. Phys. J. B"},{"key":"10.1016\/j.knosys.2026.116092_b37","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.2026.116092_b38","article-title":"Link prediction based on graph neural networks","volume":"31","author":"Zhang","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116092_b39","series-title":"Fast graph representation learning with PyTorch geometric","author":"Fey","year":"2019"},{"key":"10.1016\/j.knosys.2026.116092_b40","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.knosys.2026.116092_b41","article-title":"Collective classification in network data","volume":"29","author":"Sen","year":"2008","journal-title":"AI Mag."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600818X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600818X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:24:12Z","timestamp":1781004252000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512600818X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":41,"alternative-id":["S095070512600818X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116092","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Importance-guided neighborhood aggregation for link prediction via adaptive link representation","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116092","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"116092"}}