{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:14:08Z","timestamp":1780766048729,"version":"3.54.1"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302098"],"award-info":[{"award-number":["62302098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fujian Provincial Natural Science Foundation of China","award":["2025J01540"],"award-info":[{"award-number":["2025J01540"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tpami.2025.3603062","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:21:33Z","timestamp":1756236093000},"page":"155-169","source":"Crossref","is-referenced-by-count":5,"title":["Graph-Oriented Instruction Tuning of Large Language Models for Generic Graph Mining"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3526-6859","authenticated-orcid":false,"given":"Yanchao","family":"Tan","sequence":"first","affiliation":[{"name":"Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2566-390X","authenticated-orcid":false,"given":"Hang","family":"Lv","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5675-0468","authenticated-orcid":false,"given":"Pengxiang","family":"Zhan","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5195-9682","authenticated-orcid":false,"given":"Shiping","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Big Data Intelligence, Ministry of Education, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9145-4531","authenticated-orcid":false,"given":"Carl","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Emory University, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Hamilton","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403140"},{"key":"ref3","first-page":"31632","article-title":"Label-free node classification on graphs with large language models (LLMS)","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref4","first-page":"5711","article-title":"Harnessing explanations: LLM-to-LM interpreter for enhanced text-attributed graph representation learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"He","year":"2024"},{"key":"ref5","first-page":"20188","article-title":"One for all: Towards training one graph model for all classification tasks","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Liu","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599256"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33837"},{"key":"ref8","article-title":"GPT4graph: Can large language models understand graph structured data? an empirical evaluation and benchmarking","author":"Guo","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657775"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671987"},{"key":"ref11","first-page":"30840","article-title":"Can language models solve graph problems in natural language?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang","year":"2023"},{"key":"ref12","first-page":"1955","article-title":"Language is all a graph needs","volume-title":"Proc. Findings Assoc. Comput. Linguistics:","author":"Ye","year":"2024"},{"key":"ref13","first-page":"16302","article-title":"PRODIGY: Enabling in-context learning over graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Huang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3045924"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583493"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939754"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098036"},{"key":"ref19","first-page":"2186","article-title":"Anonymous walk embeddings","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Ivanov","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3074654"},{"key":"ref21","first-page":"11313","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Kipf","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371829"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3288280"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3038234"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3278463"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467396"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3264691"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539249"},{"key":"ref29","first-page":"8123","article-title":"A survey of graph meets large language model: Progress and future directions","volume-title":"Proc. 33th Int. Joint Conf. Artif. Intell.","author":"Li","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2005.1582432"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889733"},{"key":"ref32","article-title":"An approach to identify the most semantically informative deep representations of text and images","author":"Acevedo","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263079"},{"key":"ref34","first-page":"20884","article-title":"A topological perspective on demystifying gnn-based link prediction performance","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Wang","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1202"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583268"},{"key":"ref37","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref38","first-page":"74764","article-title":"How far can camels go? exploring the state of instruction tuning on open resources","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"ref40","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref41","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wei","year":"2022"},{"key":"ref42","first-page":"28289","article-title":"BadChain: Backdoor chain-of-thought prompting for large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xiang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref44","first-page":"1","article-title":"On the stability of fine-tuning bert: Misconceptions, explanations, and strong baselines","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Mosbach","year":"2020"},{"key":"ref45","first-page":"1","article-title":"NERDA-Con: Extending NER models for continual learning\u2013integrating distinct tasks and updating distribution shifts","volume-title":"Proc. Updatable Mach. Learn. Workshop 39th Int. Conf. Mach. Learn.","author":"Vijay","year":"2022"},{"key":"ref46","article-title":"The Llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref47","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref48","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Dettmers","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.107"},{"key":"ref50","first-page":"14884","article-title":"Parameter-efficient fine-tuning with discrete fourier transform","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Gao","year":"2024"},{"key":"ref51","first-page":"18091","article-title":"DyVal: Dynamic evaluation of large language models for reasoning tasks","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467350"},{"key":"ref53","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hu","year":"2020"},{"key":"ref54","first-page":"13308","article-title":"WalkLM: A uniform language model fine-tuning framework for attributed graph embedding","volume-title":"Proc. Adv. Neural Inf. Process. Systems.","volume":"2023","author":"Tan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.136"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref57","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107","year":"2018"},{"key":"ref58","first-page":"6437","article-title":"Training graph neural networks with 1000 layers","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Li","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nlp4convai-1.20"},{"key":"ref63","first-page":"5755","article-title":"GAP: A graph-aware language model framework for knowledge graph-to-text generation","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Colas","year":"2022"},{"key":"ref64","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2022"},{"key":"ref65","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref66","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref67","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583472"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11275622\/11141724.pdf?arnumber=11141724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T08:02:05Z","timestamp":1764835325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11141724\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":69,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3603062","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}