{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T22:05:06Z","timestamp":1779487506283,"version":"3.53.1"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.neucom.2026.133800","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:31:53Z","timestamp":1777563113000},"page":"133800","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["UniS2A: Unified semantic and structural augmentation for text-attributed graphs with large language models"],"prefix":"10.1016","volume":"690","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2105-4788","authenticated-orcid":false,"given":"Zhihong","family":"Pan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijie","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9760-8541","authenticated-orcid":false,"given":"Weisheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1205-5154","authenticated-orcid":false,"given":"Junming","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shupeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8003-570X","authenticated-orcid":false,"given":"Ronghua","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133800_bib0005","series-title":"NeurIPS","article-title":"A comprehensive study on text-attributed graphs: benchmarking and rethinking","author":"Yan","year":"2023"},{"key":"10.1016\/j.neucom.2026.133800_bib0010","series-title":"NAACL (Long Papers)","first-page":"1412","article-title":"Can LLMs convert graphs to text-attributed graphs?","author":"Wang","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0015","author":"Su"},{"issue":"3","key":"10.1016\/j.neucom.2026.133800_bib0020","doi-asserted-by":"crossref","first-page":"964","DOI":"10.26599\/BDMA.2024.9020009","article-title":"Empirical and experimental perspectives on big data in recommendation systems: a comprehensive survey","volume":"7","author":"Taha","year":"2024","journal-title":"Big Data Min. Anal."},{"issue":"5","key":"10.1016\/j.neucom.2026.133800_bib0025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3711122","article-title":"Can graph neural networks be adequately explained? A survey","volume":"57","author":"Li","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.133800_bib0030","series-title":"AAAI","first-page":"18667","article-title":"GNN-transformer cooperative architecture for trustworthy graph contrastive learning","author":"Liang","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0035","series-title":"NeurIPS","article-title":"DTGB: a comprehensive benchmark for dynamic text-attributed graphs","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0040","series-title":"WWW","first-page":"4316","article-title":"High-frequency-aware hierarchical contrastive selective coding for representation learning on text attributed graphs","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0045","series-title":"AAAI","first-page":"7024","article-title":"Attribute and structure preserving graph contrastive learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.133800_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107062","article-title":"Graph intention embedding neural network for tag-aware recommendation","volume":"184","author":"Wang","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.133800_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128595","article-title":"Adaptive denoising graph contrastive learning with memory graph attention for recommendation","volume":"610","author":"Ma","year":"2024","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133800_bib0060","series-title":"KDD","first-page":"4467","article-title":"Pre-training and prompting for few-shot node classification on text-attributed graphs","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0065","series-title":"EMNLP (Findings)","first-page":"10316","article-title":"Pretraining language models with text-attributed heterogeneous graphs","author":"Zou","year":"2023"},{"key":"10.1016\/j.neucom.2026.133800_bib0070","series-title":"KDD","first-page":"6616","article-title":"A survey of large language models for graphs","author":"Ren","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0075","series-title":"IJCAI","first-page":"5734","article-title":"Efficient tuning and inference for large language models on textual graphs","author":"Zhu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0080","series-title":"CIKM","first-page":"1836","article-title":"Distilling large language models for text-attributed graph learning","author":"Pan","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129919","article-title":"Lgkgr: a knowledge graph reasoning model using LLMs augmented gnns","volume":"635","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133800_bib0090","article-title":"LLM-agr: large language model augmented graph representation learning for recommendation","author":"Zha","year":"2025","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133800_bib0095","series-title":"KDD","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.neucom.2026.133800_bib0100","author":"Yang"},{"key":"10.1016\/j.neucom.2026.133800_bib0105","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133800_bib0110","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2025","first-page":"6815","article-title":"Heal: hybrid enhancement with LLM-based agents for text-attributed hypergraph self-supervised representation learning","author":"Li","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0115","series-title":"Findings of the Association for Computational Linguistics: ACL 2025","first-page":"6057","article-title":"Mark: multi-agent collaboration with ranking guidance for text-attributed graph clustering","author":"Fu","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0120","series-title":"ICLR (Poster)","article-title":"Deep graph infomax","author":"Velickovic","year":"2019"},{"key":"10.1016\/j.neucom.2026.133800_bib0125","series-title":"ICLR","article-title":"Infograph: unsupervised and semi-supervised graph-level representation learning via mutual information maximization","author":"Sun","year":"2020"},{"key":"10.1016\/j.neucom.2026.133800_bib0130","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133800_bib0135","series-title":"WWW","first-page":"2069","article-title":"Graph contrastive learning with adaptive augmentation","author":"Zhu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133800_bib0140","doi-asserted-by":"crossref","first-page":"10479","DOI":"10.1109\/TNNLS.2025.3545111","article-title":"Unifying attribute and structure preservation for enhanced graph contrastive learning","volume":"36","author":"Chen","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133800_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109537","article-title":"Line graph contrastive learning for link prediction","volume":"140","author":"Zhang","year":"2023","journal-title":"Pattern Recognit."},{"issue":"6","key":"10.1016\/j.neucom.2026.133800_bib0150","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.103847","article-title":"Edge contrastive learning for link prediction","volume":"61","author":"Liu","year":"2024","journal-title":"Inf. Process. Manag."},{"key":"10.1016\/j.neucom.2026.133800_bib0155","series-title":"AAAI","first-page":"19875","article-title":"SOLA-GCL: subgraph-oriented learnable augmentation method for graph contrastive learning","author":"Peng","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0160","first-page":"17238","article-title":"A comprehensive study on text-attributed graphs: benchmarking and rethinking","volume":"36","author":"Yan","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133800_bib0165","series-title":"EMNLP (Findings)","first-page":"2745","article-title":"GRENADE: graph-centric language model for self-supervised representation learning on text-attributed graphs","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.133800_bib0170","series-title":"ICLR","article-title":"Learning on large-scale text-attributed graphs via variational inference","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neucom.2026.133800_bib0175","series-title":"LoG, Vol. 269 of Proceedings of Machine Learning Research","first-page":"24","article-title":"A pure transformer pretraining framework on text-attributed graphs","author":"Song","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0180","series-title":"EMNLP","first-page":"14830","article-title":"Bridging local details and global context in text-attributed graphs","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0185","series-title":"COLING","first-page":"10865","article-title":"Text-attributed graph learning with coupled augmentations","author":"Zhou","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0190","series-title":"WWW","first-page":"2183","article-title":"Graphclip: enhancing transferability in graph foundation models for text-attributed graphs","author":"Zhu","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0195","series-title":"KDD (1)","first-page":"448","article-title":"Unigraph: learning a unified cross-domain foundation model for text-attributed graphs","author":"He","year":"2025"},{"issue":"2","key":"10.1016\/j.neucom.2026.133800_bib0200","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":"2023","journal-title":"SIGKDD Explor."},{"key":"10.1016\/j.neucom.2026.133800_bib0205","doi-asserted-by":"crossref","first-page":"8622","DOI":"10.1109\/TKDE.2024.3469578","article-title":"Large language models on graphs: a comprehensive survey","volume":"36","author":"Jin","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.133800_bib0210","series-title":"ICLR","article-title":"Harnessing explanations: LLM-to-lm interpreter for enhanced text-attributed graph representation learning","author":"He","year":"2024"},{"key":"10.1016\/j.neucom.2026.133800_bib0215","series-title":"AAAI","first-page":"13087","article-title":"Leveraging large language models for node generation in few-shot learning on text-attributed graphs","author":"Yu","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0220","author":"Sun"},{"key":"10.1016\/j.neucom.2026.133800_bib0225","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133800_bib0230","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.133800_bib0235","series-title":"WWW (Companion Volume)","first-page":"1824","article-title":"Graphit: efficient node classification on text-attributed graphs with prompt optimized LLMs","author":"Khoshraftar","year":"2025"},{"key":"10.1016\/j.neucom.2026.133800_bib0240","series-title":"ICML Workshop on Graph Representation Learning and Beyond","article-title":"Deep graph contrastive representation learning","author":"Zhu","year":"2020"},{"key":"10.1016\/j.neucom.2026.133800_bib0245","series-title":"The Tenth International Conference on Learning Representations, ICLR","article-title":"Large-scale representation learning on graphs via bootstrapping","author":"Thakoor","year":"2022"},{"key":"10.1016\/j.neucom.2026.133800_bib0250","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109631","article-title":"Graph barlow twins: a self-supervised representation learning framework for graphs","volume":"256","author":"Bielak","year":"2022","journal-title":"Knowl. Based Syst."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011975?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011975?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T21:24:44Z","timestamp":1779485084000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226011975"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":50,"alternative-id":["S0925231226011975"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133800","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"UniS2A: Unified semantic and structural augmentation for text-attributed graphs with large language models","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133800","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":"133800"}}