{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:58:36Z","timestamp":1785488316006,"version":"3.56.0"},"reference-count":54,"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\/100003187","name":"NSF","doi-asserted-by":"publisher","award":["III-2106758"],"award-info":[{"award-number":["III-2106758"]}],"id":[{"id":"10.13039\/100003187","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100003187","name":"NSF","doi-asserted-by":"publisher","award":["POSE-2346158"],"award-info":[{"award-number":["POSE-2346158"]}],"id":[{"id":"10.13039\/100003187","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013141","name":"Jilin Provincial Key Research and Development Plan Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013141","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476110"],"award-info":[{"award-number":["62476110"]}],"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":["U2341229"],"award-info":[{"award-number":["U2341229"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004032","name":"Jilin University","doi-asserted-by":"publisher","award":["20240304200SF"],"award-info":[{"award-number":["20240304200SF"]}],"id":[{"id":"10.13039\/501100004032","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.artint.2026.104584","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T16:19:31Z","timestamp":1781453971000},"page":"104584","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Towards context-aware graph representation learning: Adaptive node aggregation with LLMs"],"prefix":"10.1016","volume":"358","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6149-3214","authenticated-orcid":false,"given":"Songwei","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4629-9901","authenticated-orcid":false,"given":"Yuan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0315-3547","authenticated-orcid":false,"given":"Sinuo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8658-9447","authenticated-orcid":false,"given":"Jifeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hechang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.artint.2026.104584_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2022.103708","article-title":"Multi-view graph convolutional networks with attention mechanism","volume":"307","author":"Yao","year":"2022","journal-title":"Artif. Intell."},{"key":"10.1016\/j.artint.2026.104584_bib0002","series-title":"International Conference on Machine Learning","first-page":"24737","article-title":"Path neural networks: expressive and accurate graph neural networks","author":"Michel","year":"2023"},{"key":"10.1016\/j.artint.2026.104584_bib0003","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"13383","article-title":"GRAIN: multi-granular and implicit information aggregation graph neural network for heterophilous graphs","volume":"vol. 39","author":"Zhao","year":"2025"},{"key":"10.1016\/j.artint.2026.104584_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2024.104129","article-title":"Polarized message-passing in graph neural networks","volume":"331","author":"He","year":"2024","journal-title":"Artif. Intell."},{"key":"10.1016\/j.artint.2026.104584_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2024.104078","article-title":"Saliency-aware regularized graph neural network","volume":"328","author":"Pei","year":"2024","journal-title":"Artif. Intell."},{"key":"10.1016\/j.artint.2026.104584_bib0006","series-title":"The Web Conference 2024","article-title":"GNNs as adapters for LLMs on text-attributed graphs","author":"Huang","year":"2024"},{"key":"10.1016\/j.artint.2026.104584_bib0007","first-page":"1","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"Mikolov","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2026.104584_bib0008","doi-asserted-by":"crossref","unstructured":"Z.S. Harris, Distributional structure, Word, 10 (2-3) (1954) 146\u2013162.","DOI":"10.1080\/00437956.1954.11659520"},{"issue":"10","key":"10.1016\/j.artint.2026.104584_bib0009","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1007\/s11431-020-1647-3","article-title":"Pre-trained models for natural language processing: a survey","volume":"63","author":"Qiu","year":"2020","journal-title":"Sci. China Technol. Sci."},{"key":"10.1016\/j.artint.2026.104584_bib0010","series-title":"Proceedings of the 5th Workshop on Representation Learning for NLP","first-page":"110","article-title":"Contextual and non-contextual word embeddings: an in-depth linguistic investigation","author":"Miaschi","year":"2020"},{"issue":"240","key":"10.1016\/j.artint.2026.104584_bib0011","first-page":"1","article-title":"PaLM: scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.artint.2026.104584_bib0012","unstructured":"H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi\u00e8re, N. Goyal, E. Hambro, F. Azhar, et al., LLaMA: open and efficient foundation language models, (2023). arXiv preprint arXiv: 2302.13971."},{"key":"10.1016\/j.artint.2026.104584_bib0013","unstructured":"J. Wei, M. Bosma, V.Y. Zhao, K. Guu, A.W. Yu, B. Lester, N. Du, A.M. Dai, Q.V. Le, Finetuned language models are zero-shot learners, (2021). arXiv preprint arXiv: 2109.01652."},{"key":"10.1016\/j.artint.2026.104584_bib0014","first-page":"13260","article-title":"Principal neighbourhood aggregation for graph nets","volume":"33","author":"Corso","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2026.104584_bib0015","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7370","article-title":"Graph convolutional networks for text classification","volume":"vol. 33","author":"Yao","year":"2019"},{"issue":"6","key":"10.1016\/j.artint.2026.104584_bib0016","doi-asserted-by":"crossref","first-page":"3118","DOI":"10.1109\/TKDE.2025.3547817","article-title":"A flexible diffusion convolution for graph neural networks","volume":"37","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"10.1016\/j.artint.2026.104584_bib0017","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1145\/3655103.3655110","article-title":"Exploring the potential of large language models (llms) in learning on graphs","volume":"25","author":"Chen","year":"2024","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"10.1016\/j.artint.2026.104584_bib0018","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"747","article-title":"GAugLLM: improving graph contrastive learning for text-attributed graphs with large language models","author":"Fang","year":"2024"},{"key":"10.1016\/j.artint.2026.104584_bib0019","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2026.104584_bib0020","series-title":"Proceedings of the ACM Web Conference 2023","first-page":"417","article-title":"GraphPrompt: unifying pre-training and downstream tasks for graph neural networks","author":"Liu","year":"2023"},{"key":"10.1016\/j.artint.2026.104584_bib0021","unstructured":"T.N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks, (2016). arXiv preprint arXiv: 1609.02907."},{"key":"10.1016\/j.artint.2026.104584_bib0022","unstructured":"P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Lio, Y. Bengio, Graph attention networks, (2017). arXiv preprint arXiv: 1710.10903."},{"key":"10.1016\/j.artint.2026.104584_bib0023","unstructured":"K. Duan, Q. Liu, T.-S. Chua, S. Yan, W.T. Ooi, Q. Xie, J. He, SimTeG: a frustratingly simple approach improves textual graph learning, (2023). arXiv preprint arXiv: 2308.02565."},{"key":"10.1016\/j.artint.2026.104584_bib0024","series-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"491","article-title":"GraphGPT: graph instruction tuning for large language models","author":"Tang","year":"2024"},{"key":"10.1016\/j.artint.2026.104584_bib0025","unstructured":"T.B. Brown, Language models are few-shot learners, (2020). arXiv preprint arXiv: 2005.14165."},{"key":"10.1016\/j.artint.2026.104584_bib0026","unstructured":"Z. Hou, H. Li, Y. Cen, J. Tang, Y. Dong, GraphAlign: pretraining one graph neural network on multiple graphs via feature alignment, (2024). arXiv preprint arXiv: 2406.02953."},{"key":"10.1016\/j.artint.2026.104584_bib0027","series-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","first-page":"157","article-title":"Train your own GNN teacher: graph-aware distillation on textual graphs","author":"Mavromatis","year":"2023"},{"key":"10.1016\/j.artint.2026.104584_bib0028","unstructured":"J. Guo, L. Du, H. Liu, M. Zhou, X. He, S. Han, GPT4Graph: can large language models understand graph structured data? an empirical evaluation and benchmarking, (2023). arXiv preprint arXiv: 2305.15066."},{"key":"10.1016\/j.artint.2026.104584_bib0029","first-page":"1","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.artint.2026.104584_bib0030","series-title":"Artificial Intelligence and Statistics","first-page":"464","article-title":"Generalizing pooling functions in convolutional neural networks: mixed, gated, and tree","author":"Lee","year":"2016"},{"key":"10.1016\/j.artint.2026.104584_bib0031","unstructured":"C. Cai, Y. Wang, A simple yet effective baseline for non-attributed graph classification, (2018). arXiv preprint arXiv: 1811.03508."},{"key":"10.1016\/j.artint.2026.104584_bib0032","first-page":"1","article-title":"Understanding the representation power of graph neural networks in learning graph topology","volume":"32","author":"Dehmamy","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2026.104584_bib0033","unstructured":"H. Pei, Y. Li, H. Deng, J. Hai, P. Wang, J. Ma, J. Tao, Y. Xiong, X. Guan, Multi-track message passing: tackling oversmoothing and oversquashing in graph learning via preventing heterophily mixing, in: Forty-first International Conference on Machine Learning."},{"key":"10.1016\/j.artint.2026.104584_bib0034","series-title":"An Introduction to Algebraic Topology","volume":"vol. 119","author":"Rotman","year":"2013"},{"issue":"1","key":"10.1016\/j.artint.2026.104584_bib0035","doi-asserted-by":"crossref","first-page":"177","DOI":"10.4064\/fm-20-1-177-190","article-title":"Drei S\u00e4tze \u00fcber die n-dimensionale euklidische Sph\u00e4re","volume":"20","author":"Borsuk","year":"1933","journal-title":"Fundam. Math."},{"key":"10.1016\/j.artint.2026.104584_bib0036","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1023\/A:1009953814988","article-title":"Automating the construction of internet portals with machine learning","volume":"3","author":"McCallum","year":"2000","journal-title":"Inf. Retr."},{"key":"10.1016\/j.artint.2026.104584_bib0037","series-title":"Proceedings of the Third ACM Conference on Digital Libraries","first-page":"89","article-title":"CiteSeer: an automatic citation indexing system","author":"Giles","year":"1998"},{"key":"10.1016\/j.artint.2026.104584_bib0038","doi-asserted-by":"crossref","unstructured":"S. Prithviraj, G. Namata, M. Bilgic, L. Getoor, B. Galligher, T. Eliassi-Rad, Collective classification in network data, AI Mag. 29(3) (2008) 93\u201393.","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"10.1016\/j.artint.2026.104584_bib0039","first-page":"22118","article-title":"Open graph benchmark: datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2026.104584_bib0040","unstructured":"X. He, X. Bresson, T. Laurent, A. Perold, Y. LeCun, B. Hooi, Harnessing explanations: LLM-to-LM interpreter for enhanced text-attributed graph representation learning, (2023). arXiv preprint arXiv: 2305.19523."},{"key":"10.1016\/j.artint.2026.104584_bib0041","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.artint.2026.104584_bib0042","unstructured":"J. Gasteiger, A. Bojchevski, S. G\u00fcnnemann, Predict then propagate: graph neural networks meet personalized pagerank, (2018). arXiv preprint arXiv: 1810.05997."},{"key":"10.1016\/j.artint.2026.104584_bib0043","unstructured":"E. Chien, J. Peng, P. Li, O. Milenkovic, Adaptive universal generalized pagerank graph neural network, (2020). arXiv preprint arXiv: 2006.07988."},{"key":"10.1016\/j.artint.2026.104584_bib0044","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"17220","article-title":"Robust node classification on graph data with graph and label noise","volume":"vol. 38","author":"Zhu","year":"2024"},{"key":"10.1016\/j.artint.2026.104584_bib0045","unstructured":"M. Park, J. Heo, D. Kim, Mitigating oversmoothing through reverse process of GNNs for heterophilic graphs, in: Forty-first International Conference on Machine Learning."},{"key":"10.1016\/j.artint.2026.104584_bib0046","first-page":"19314","article-title":"Iterative deep graph learning for graph neural networks: better and robust node embeddings","volume":"33","author":"Chen","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.artint.2026.104584_bib0047","unstructured":"Y. Gao, H. Yang, P. Zhang, C. Zhou, Y. Hu, GraphNAS: graph neural architecture search with reinforcement learning, (2019). arXiv preprint arXiv: 1904.09981."},{"key":"10.1016\/j.artint.2026.104584_bib0048","unstructured":"J. Zhao, M. Qu, C. Li, H. Yan, Q. Liu, R. Li, X. Xie, J. Tang, Learning on large-scale text-attributed graphs via variational inference, (2022). arXiv preprint arXiv: 2210.14709."},{"key":"10.1016\/j.artint.2026.104584_bib0049","unstructured":"Z. Guo, L. Xia, Y. Yu, Y. Wang, Z. Yang, W. Wei, L. Pang, T.-S. Chua, C. Huang, GraphEdit: large language models for graph structure learning, (2024). arXiv preprint arXiv: 2402.15183."},{"key":"10.1016\/j.artint.2026.104584_bib0050","unstructured":"H. Liu, J. Feng, L. Kong, N. Liang, D. Tao, Y. Chen, M. Zhang, One for all: towards training one graph model for all classification tasks, (2023). arXiv preprint arXiv: 2310.00149."},{"key":"10.1016\/j.artint.2026.104584_bib0051","doi-asserted-by":"crossref","unstructured":"N. Reimers, Sentence-BERT: sentence embeddings using siamese BERT-Networks, (2019). arXiv preprint arXiv: 1908.10084.","DOI":"10.18653\/v1\/D19-1410"},{"key":"10.1016\/j.artint.2026.104584_bib0052","unstructured":"I. Beltagy, K. Lo, A. Cohan, SciBERT: a pretrained language model for scientific text, (2019). arXiv preprint arXiv: 1903.10676."},{"key":"10.1016\/j.artint.2026.104584_bib0053","unstructured":"R. Anil, A.M. Dai, O. Firat, M. Johnson, D. Lepikhin, A. Passos, S. Shakeri, E. Taropa, P. Bailey, Z. Chen, et al., PaLM 2 technical report, (2023). arXiv preprint arXiv: 2305.10403."},{"key":"10.1016\/j.artint.2026.104584_bib0054","unstructured":"J. Bai, S. Bai, Y. Chu, Z. Cui, K. Dang, X. Deng, Y. Fan, W. Ge, Y. Han, F. Huang, et al., Qwen technical report, (2023). arXiv preprint arXiv: 2309.16609."}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370226001104?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370226001104?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:14:41Z","timestamp":1785485681000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0004370226001104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":54,"alternative-id":["S0004370226001104"],"URL":"https:\/\/doi.org\/10.1016\/j.artint.2026.104584","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Towards context-aware graph representation learning: Adaptive node aggregation with LLMs","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artint.2026.104584","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":"104584"}}